JP2016539760A - Adaptive interface for continuous monitoring devices - Google Patents

Abstract

Systems and methods are described that continuously adapt aspects of a continuous monitoring device based on collected information to provide individually tailored configurations. Adaptation can include adapting user interfaces, alerting, motivational messages, training, and the like. Such adaptation may allow the patient to more easily identify and understand the information provided by / via the device.

Description

INCORPORATION BY RELATED APPLICATIONS Any and all priority claims specified in the application data sheet or any amendments thereto are incorporated herein by reference under 37 CFR 1.57. This application claims the benefit of US Provisional Application No. 61 / 898,300, filed Oct. 31, 2013. The foregoing applications are hereby incorporated by reference in their entirety and each is expressly incorporated herein by reference.

  The development relates generally to medical devices such as continuous glucose sensors, including systems and methods for adaptive interface processing of sensor data.

  Diabetes mellitus is a disorder in which the pancreas cannot make enough insulin (type I or insulin dependent) and / or insulin is ineffective (type 2 or non-insulin dependent). In diabetic conditions, the affected person suffers from high glucose, which can cause a range of physiological disorders associated with microvascular degradation (eg, renal failure, skin ulcers, or bleeding into the vitreous of the eye). A hypoglycemic response (low glucose) can be caused by inadvertent overdose of insulin, or by extreme exercise or inadequate food intake after normal dosing of insulin or glucose lowering agents.

  Traditionally, a person suffering from diabetes carries a self-monitoring blood glucose (SMBG) monitor, which typically requires an uncomfortable finger puncture to obtain a blood sample for measurement. Due to the lack of comfort and convenience associated with finger puncture, a person suffering from diabetes usually only measures glucose levels 2-4 times a day. Unfortunately, the interval between measurements may be so far away that a person suffering from diabetes is too late to notice a hyperglycemic or hypoglycemic condition and sometimes suffers dangerous side effects. Not only do patients with diabetes tend to get SMBG levels in a timely manner, but patients also have their blood glucose levels elevated (higher) or decreased based on conventional methods. There is a tendency not to know whether it is lower (lower). Diabetic patients may therefore be prevented from making knowledge-based insulin therapy decisions.

  Another device used by diabetics to monitor blood glucose is a continuous analyte sensor. Continuous analyte sensors typically include sensors that are placed subcutaneously, transdermally (eg, transdermally), or in a blood vessel. The sensor measures the concentration of a given analyte in the body and generates an original signal that is transmitted to the electronics associated with the sensor. The original signal is converted into an output value, which is displayed on the display. The output value resulting from the conversion of the original signal is typically expressed in a format that provides meaningful information to the user, for example, blood glucose expressed in mg / dL. Unfortunately, widespread adoption of continuous analyte sensors has so far been hampered by a “one size fits” approach to system design.

  A system that continuously adapts to provide individually tailored configurations based on collected information is an adaptive and interactive health care aid for chronic management of disease in an outpatient setting. Improvements are believed to improve broad adoption. Adaptation may include adapting the user interface, alerting, motivational messages, training, etc. Such adaptation may allow the patient to more easily identify and understand the information provided by / via the device.

  In a first innovative aspect, a method for adaptive configuration of an analyte monitoring device is provided. The method includes transmitting a first report relating to the subject's physiological information using a first report format that includes a first report format characteristic. The method further includes determining at least one of behavior or situation information including at least one behavior or situation characteristic for the subject. The method also includes comparing at least one behavior and / or situation characteristic to one or more behavior or situation criteria. The method further includes adjusting a report format based at least in part on the comparison, the report format including a second report format characteristic that is different from the first report format characteristic. The method further includes transmitting a second report regarding physiological information using the second report format.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the first report provides physiological information over a period of time. Includes a trend graph.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the determination of behavioral or status information is associated with the patient. Receiving a message containing data from the sensor, identifying a characteristic extractor based on the message and sensor, and at least one behavior or situation characteristic based on the received message via the identified characteristic extractor. Generating, as well as associating the generated characteristics with behavioral or situational information.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the characteristics are compared to one or more behavior or situation criteria Doing includes comparing the characteristics to behavior or situation criteria associated with the goal.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the characteristics are compared to one or more behavior or situation criteria Doing includes comparing characteristics to behavioral or contextual criteria associated with interface adaptation. In some implementations, interface adaptation may include alert frequency, alert volume, alert tone, display font, display font size, display font color, message destination address, message destination phone number, menu item list, or analyte monitoring. It includes at least one of the device operation settings.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the method further transmits a message identifying the adjustment. As well as triggering a second report format for subsequent reports upon receipt of adjustment confirmation, and for subsequent reports if a rejection of adjustment or no response to the message is received Invoking the first report format.

  In a generally applicable embodiment of the first aspect (ie, independently combinable with any of the aspects or embodiments specified herein), the first report is common with the second report To the destination.

  In a generally applicable embodiment of the first aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the first report is transmitted to the first destination And the second report is transmitted to the second destination.

  In a second innovative aspect, a method for identifying individual adaptation information is provided. The method includes capturing a value indicative of a behavior or situation associated with an individual's physiological state from pre-identified input. The method further includes periodically storing additional values received from the pre-specified inputs, wherein a user-specific pre-specified input value record is created. The method further includes periodically determining behavior or status information about the individual based on a record of user-specific pre-specified inputs.

  In a generally applicable embodiment of the second aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the method further comprises a determined behavior or Includes transmitting status information.

  In a generally applicable embodiment of the second aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the transmission is a continuous monitoring device, patient record system, Including transmission to smartphones or social media internet sites.

  In a generally applicable embodiment of the second aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the pre-specified input is a blood glucose meter, a thermometer, It includes at least one of an accelerometer, a camera, a microphone, a query processing engine, an electronic device configured for communication between machines, or an electronic patient record.

  In a generally applicable embodiment of the second aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), storing additional values periodically Including storing a time stamp indicating when a particular additional value was stored.

  In a generally applicable embodiment of the second aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the physiological condition is diabetes, obesity, malnutrition, Includes one or more of hyperactivity, depression, or fertility.

  In a generally applicable embodiment of the second aspect (i.e., can be combined independently with any of the aspects or embodiments specified herein), determining behavioral or status information about the individual comprises Selecting one of a plurality of pre-specified input values included in the record, and an input providing the selected value and the selected value, and an identification value associated with the plurality of behaviors or situations Identifying one or more behaviors or situations based on the comparison.

  In a generally applicable embodiment of the second aspect (i.e., can be combined independently with any of the aspects or embodiments specified herein), determining behavioral or status information about the individual comprises Includes processing the predefined input values included in the record.

  In a generally applicable embodiment of the second aspect (ie, combinable independently of any of the aspects or embodiments specified herein), the value processing is to identify a value trend. including.

  In a third innovative aspect, a method is provided for performing adaptive goal setting for an individual. The method includes obtaining first behavior or status information associated with the individual. The method further includes obtaining second behavior or context information associated with a plurality of individuals having characteristics in common with the individual. The method includes generating one or more behavior or situation criteria for the goal based on the acquired first information and the acquired second information. The method also includes generating a goal based on the generated criteria.

  In a generally applicable embodiment of the third aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the method also includes at least one behavior or situation criterion. Providing a predetermined goal comprising: generating the goal includes modifying at least one behavior or status criterion of the predetermined goal based on the one or more behavior or status criteria generated .

  In a generally applicable embodiment of the third aspect (ie, independently combinable with any of the aspects or embodiments specified herein), the method also presents the generated goal. For providing via a human detectable interface and receiving a message to activate the target.

  In a fourth innovative aspect, an adaptive teaching method is provided. The method includes identifying a need for training or a need for required instruction based on behavior / situation information about the user. The method also includes providing training or guidance based on physiological information associated with behavior / situation information about the user in response to the identified needs.

  In a generally applicable embodiment of the fourth aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the behavior or status information is a structured query or natural language Contains a query.

  In a generally applicable embodiment of the fourth aspect (ie, can be combined independently with any of the aspects or embodiments specified herein), the method also provides feedback associated with training or guidance. And reprocessing the training or instruction further considering the received feedback.

  In a fifth innovative aspect, an integrated system is provided for monitoring glucose concentration in a host and for delivering insulin to the host. The system includes a continuous glucose sensor configured to measure glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host. The system further includes an insulin delivery device configured to deliver insulin to the host and operably connected to a continuous glucose sensor. The system also includes a processor module that is configured to perform, in whole or in part, any of the four innovative methods described above.

  In a sixth innovative aspect, an electronic device for monitoring glucose concentration in a host is provided. The device includes a continuous glucose sensor configured to measure glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host. The device further includes a processor module that is configured to perform, in whole or in part, any of the four innovative methods described above.

  In a seventh innovative aspect, an electronic device for delivering insulin to a host is provided. The device includes an insulin delivery device configured to deliver insulin to a host and operably connected to a continuous glucose sensor. The device also includes a processor module that is configured to perform, in whole or in part, any of the four innovative methods described above.

  In an eighth innovative aspect, a system for adaptive configuration of an analyte monitoring device is provided. The system includes an input receiver configured to receive at least one of status information, behavior information, or physiological information about the user over a period of time. The system includes an input processor configured to identify a situation or behavior based at least in part on information received over time. The system further includes an adaptation engine configured to determine an adaptation of the analyte monitoring device based on the identified situation or behavior.

  Any of the features of the embodiments of the first, second, third, fourth, fifth, sixth, seventh, or eighth aspect apply to all aspects and embodiments specified herein. Is possible. Furthermore, any of the features of the embodiments of the first, second, third, fourth, sixth, seventh, or eighth aspect are independently described in any other way than described herein. Embodiments can be combined partially or wholly, for example, 1, 2, or 3 or more embodiments can be combined in whole or in part. Further, any of the features of the first, second, third, fourth, or fifth, sixth, seventh, or eighth embodiment may be optional with respect to other aspects or embodiments. Any aspect or embodiment of a method may be performed by a system or apparatus of another aspect or embodiment, and any aspect or embodiment of the system is configured to perform a method of another aspect or embodiment Can be done.

1 is a block diagram of a preferred embodiment integrated system including a continuous glucose sensor and a pharmaceutical delivery device. FIG. FIG. 6 is a process flow diagram of a method for adjusting an interface type / style of physiological information based on behavioral and / or situational information. Figure 6 shows a plot of a histogram (or distribution) of carbohydrates contained in a meal over a 30 day period. FIG. 5 is a process flow diagram of a method for determining patient behavior and / or status information. FIG. 6 is a process flow diagram of a method for determining a goal or criteria used in one or more aspects described. FIG. 6 is a process flow diagram of a method for providing patient training, improvements in diabetes management, and / or short term recommendations. FIG. 2 is a functional block diagram of a continuous monitoring device including an adaptive interface.

  Consider a specific example of continuous glucose monitoring. For diabetics, glucose monitoring can literally be a matter of separating life and death. The characteristics of a glucose monitor user differ in many aspects. Each has its own medical need. Each user has an individual level of expertise. Each user has a unique educational background, language, and cultural association. Each user participates in his / her own activities with various degrees of zeal. Furthermore, the properties are not static, i.e. they can change over time. These are a few factors that can affect how, when, and why a patient uses (or chooses to ignore) a glucose monitor.

  One non-limiting advantage of the described property is to provide a patient adapted interface. Adaptation considers active and / or passive data associated with the patient in order to generate an interface suitable for the patient's unique characteristics and behavior. Rather than adjusting the interface statically according to preference, dynamically adjusting the interface improves the patient's monitoring device experience and ultimately makes it more consistent with adherence to prescribed treatment plans Can help achieve accurate device use. In addition, the system continuously evaluates the means that the system and / or user can adjust to maximize the desired result (s) when data is available. Can be configured to identify adaptations in real time.

  The following description and examples illustrate in detail some exemplary embodiments of the disclosed invention. Those skilled in the art will recognize that there are numerous variations and modifications of this invention that are encompassed by its scope. Accordingly, the description of certain exemplary embodiments is not to be taken as limiting the scope of the invention.

  In order to facilitate understanding of the properties described, continuous glucose monitoring is used as part of the following description. It will be appreciated that the adaptive systems and methods described are applicable to other continuous monitoring systems. For example, features considered include lactate, free fatty acids, exercise heart rate, IgG-antigliadin, insulin, glucagon, movement tracking, fertility, caloric intake, hydration, salt concentration, sweat / sweat (stress) , Ketones, adipanectin, troponin, sweating and / or body temperature can be used for continuous monitoring. If glucose monitoring is used as an example, one or more of these alternative monitoring condition examples may be replaced.

  The term “continuous glucose sensor”, as used herein, is broad and shall be given its usual and customary meaning to those skilled in the art (not limited to a special or dedicated meaning); In general, devices that measure the glucose concentration of body fluids (eg blood, plasma, intestinal fluid, etc.) continuously or continuously, for example from just a moment, for example at intervals ranging from 1, 2, or 5 minutes or more. Point to. A continuous or continuous glucose sensor can be used without requiring user activation and / or interaction for each measurement, as described, for example, with reference to US Pat. No. 6,001,067. It should be understood that glucose concentration can be measured automatically.

  As used herein, the phrase “continuous glucose sensing” or “continuous glucose monitoring” is a broad term and is given its ordinary and customary meaning to those skilled in the art (in a special or dedicated sense). In general, monitoring of the glucose concentration of a host body fluid (eg, blood, serum, plasma, extracellular fluid, etc.) is in the range of, for example, only a moment, eg, 1, 2, or 5 minutes or more. It is a period that is continuously or continuously performed at a time interval of. In one exemplary embodiment, the glucose concentration of the host extracellular fluid is measured every 1, 2, 5, 10, 20, 30, 40, 50, or 60 seconds.

  As used herein, the term “substantially” is a broad term and is intended to be given its usual and customary meaning to one of ordinary skill in the art (not limited to a special or dedicated meaning), The majority of what is manifested, but not necessarily the whole, includes more than 50 percent, more than 60 percent, more than 70 percent, more than 80 percent, more than 90 percent , Or more.

  As used herein, the terms “processor” and “processor module” are broad terms and are intended to be given their ordinary and customary meaning (not limited to special or dedicated meanings) to those skilled in the art, Refers to a computer system, state machine, processor, etc. designed to perform mathematical or logical operations using logic circuitry in response to and processing basic instructions that drive a computer. In some embodiments, the term may include ROM and / or RAM associated therewith.

  As used herein, the term “host” generally refers to animals (eg, mammals such as humans) and plants. The terms “subject” and “individual” may be used interchangeably with “host” in certain embodiments. As used herein, the term “user” typically uses information obtained from a sensor, inputs information to the sensor, or otherwise interacts with the sensor directly or through an interface. It refers to what to do. In certain embodiments, the user may be a host, eg, an individual that utilizes data from a continuous glucose sensor for self-monitoring of glucose levels. In certain embodiments, the user and host are different, e.g., to select an insulin treatment protocol for a parent who uses data from a continuous glucose sensor to monitor a child's glucose level, or a patient with diabetes. A medical worker who uses data from a continuous glucose sensor.

  Exemplary embodiments disclosed herein relate to the use of a glucose sensor to measure a substance that is indicative of glucose concentration or analyte concentration or presence. In some embodiments, the glucose sensor is a continuous device, such as a subcutaneous, transdermal, transdermal, non-invasive, and / or intravascular (eg, intravenous) device. In some embodiments, the device may analyze multiple intermittent blood samples. Glucose sensors can be enzymatic, chemical, physical, electrochemical, optical, photochemical, fluorescence-based, spectrophotometric, spectroscopic (eg, optical absorption spectroscopy, Raman spectroscopy, etc.), polarimetric Any glucose measurement method can be used, including calorimetric, iontophoretic, radiometric, and the like.

  The glucose sensor may provide a data stream that indicates the concentration of the analyte in the host using any known detection method, including invasive, minimally invasive, and non-invasive sensing techniques. A data stream is typically an original data signal used to provide useful analyte values to a user, such as a patient or healthcare professional (eg, a physician) who may use the sensor.

  Although most of the description and examples relate to glucose sensors, system and method embodiments can be applied to any measurable analyte. In some embodiments, the analyte sensor is a glucose sensor that can measure the concentration of glucose in the host. Some exemplary embodiments described below use an implantable glucose sensor. However, it should be understood that the devices and methods described herein are applicable to any device that can detect an analyte concentration and provide an output representative of the analyte concentration.

  In some embodiments, the analyte sensor is an implantable glucose sensor such as that described by reference to US Pat. No. 6,0011,067 and US Patent Publication No. US-2011-0027127-A1. is there. In some embodiments, the analyte sensor is a transdermal glucose sensor such as that described by reference to US Patent Publication No. US-2006-0020187-A1. In still other embodiments, the analyte sensor is a dual electrode analyte sensor such as that described by reference to US Patent Publication No. US-2009-0137887-A1. In still other embodiments, the sensor is configured to be implanted in a host vessel or outside the body, such as those described in US Patent Publication No. US-2007-0027385-A1. These patents and publications are incorporated herein by reference in their entirety.

  FIG. 1 is a block diagram of a preferred embodiment integrated system including a continuous glucose sensor and a drug delivery device. FIG. 1 illustrates an exemplary environment in which some embodiments described herein may be implemented. Here, the analyte monitoring system 100 includes a continuous analyte sensor system 8. Continuous analyte sensor system 8 includes a sensor electronics module 12 and a continuous analyte sensor 10. The system 100 may also include other devices and / or sensors such as a drug delivery pump 2 and a reference meter 4 as illustrated in FIG. The continuous analyte sensor 10 can be physically connected to the sensor electronics module 12 and can be integrated into the continuous analyte sensor 10 (eg, non-removably attached thereto) or removed. Can be attached as possible. Alternatively, the continuous analyte sensor 10 may be physically separated from the sensor electronics module 12, but may be electronically connected by inductive coupling or the like. In addition, the sensor electronics module 12, the drug delivery pump 2, and / or the analyte reference meter 4 may include one or more additional devices, such as some or all of the display devices 14, 16, 18, and 20. Can communicate.

  The system 100 of FIG. 1 is also directly or indirectly via a network 24 from one or more of the sensor system 8, the drug delivery pump 2, the reference analyte meter 4, and the display devices 14, 16, 18, 20. Including a cloud-based processor 22 configured to analyze analyte data, drug delivery data, and / or other patient-related data provided to Based on the received data, the processor 22 further processes the data, generates a report that provides statistics based on the processed data, triggers a notification to an electronic device associated with the host or the host caregiver, or The processed information can be provided to any of the other devices in FIG. In some exemplary implementations, the cloud-based processor 22 includes one or more servers. If the cloud-based processor 22 includes multiple servers, the servers can be either geographically local or remote from each other. Network 24 may include any wired and wireless communication medium for transmitting data, including WiFi networks, cellular networks, the Internet, and any combination thereof.

  The example implementation described with respect to FIG. 1 refers to the analyte data being received by the processor 22, although other types of processing data and raw data are described in more detail herein. It should be understood that it can be received.

  In some exemplary implementations, sensor electronics module 12 may include electronic circuitry associated with measuring and processing data generated by continuous analyte sensor 10. This generated continuous analyte sensor data may also include algorithms that can be used to process and calibrate the continuous analyte sensor data, although these algorithms may be provided by other means as well. Good. The sensor electronics module 12 may include hardware, firmware, software, or a combination thereof to provide analyte level measurements via a continuous analyte sensor, such as a continuous glucose sensor.

  Sensor electronics module 12 may be connected to one or more devices, such as some or all of display devices 14, 16, 18, and 20, as shown (eg, wirelessly, etc.). Display devices 14, 16, 18, and / or 20 may be configured to process and present information, such sensor information being transmitted by sensor electronics module 12 for display on the display device. . Display devices 14, 16, 18, and 20 may also trigger an alarm based on the analyte sensor data.

  1, display device 14 is a key fob-like display device, and display device 16 is a portable application-specific computing device 16 (eg, a DexCom G4® Platinum receiver commercially available from DexCom, Inc.). And the display device 18 is a general-purpose smartphone or tablet computing device 20 (for example, Apple (registered trademark) iPhone (registered trademark), iPad (registered trademark), or ipod touch (registered trademark) commercially available from Apple, Inc. The display device 20 is a computer workstation 20. In some exemplary implementations, the relatively small key fob-like display device 14 is a wristwatch, belt, necklace, pendant, piece of jewelry, adhesive patch, pager, key fob, plastic card (eg, credit card). ), A computing device embodied in an identification (ID) card or the like. The small display device 14 may include a relatively small display (eg, smaller than the display device 18) and is configured to display a limited set of displayable sensor information, such as numerical values 26 and arrows 28. obtain. Some systems are also referred to as “Devices Used in Connection with Continuous Analyzing That Provided the User with One of More Notifications, and the United States Application, and the Related Applications, United States Patent Application No. 61 / Rel. The entire wearable device 21 may be included, such as those described in US Pat. No. 896,597, the entire disclosure of which is expressly incorporated herein by reference. The wearable device 21 may include any device (s) that are worn or integrated into the user's field of view, clothing, and / or body. Exemplary devices include wearable devices, anklets, glasses, rings, necklaces, armbands, pendants, belt clips, hair clips / ties, pins, cuff links, tattoos, stickers, socks, sleeves, gloves, clothing (eg, skirts) , Trousers, underwear, bras, etc.), "garment ornaments", for example, zipper handles, buttons, watches, shoes, contact lenses, subcutaneous implants, cochlear implants, shoe inserts, orthodontic appliances (mouth), orthodontic appliances (Body), bandages (medical wrapping), sports bands (wristbands, headbands), hats, bandages, hair weaves (hair weaves), nail polish, artificial joints / body parts, orthopedic Pin / device, implantable heart or neurology Device and the like. The small display device 14 and / or the wearable device 21 may include a relatively small display (eg, smaller than the display device 18), and a graphical and / or numerical representation of sensor information, such as a numerical value 26 and / or an arrow 28. May be configured to display. In contrast, display devices 16, 18, and 20 provide a larger set of displayable information, such as trend graph 30, depicted on portable receiver 16, in addition to other information such as numerical values and arrows. It can be a larger display device that can be displayed.

  Any other user equipment (eg, computing device) configured to present at least information (eg, drug delivery information, individual self-monitoring analyte readouts, heart rate monitors, calorie intake monitors, etc.) It should be understood that can be used in addition to or in place of those discussed with reference to FIG.

  In some exemplary implementations of FIG. 1, the continuous analyte sensor 10 comprises a sensor for detecting and / or measuring an analyte, the continuous analyte sensor 10 being a non-invasive device, a subcutaneous device. As a transdermal device and / or an intravascular device, it can be configured to continuously detect and / or measure an analyte. In some exemplary implementations, the continuous analyte sensor 10 can analyze multiple intermittent blood samples, although other analytes can be used as well.

  In some exemplary implementations of FIG. 1, the continuous analyte sensor 10 may be enzymatic, chemical, physical, electrochemical, fluorescent, spectrophotometric, polarimetric, calorimetric, iontophoresis, iontophoresis. A glucose sensor may be provided that is configured to measure glucose in the blood using one or more measurement techniques, such as mechanical, radiometric, immunochemical, and the like. In implementations where the continuous analyte sensor 10 includes a glucose sensor, the glucose sensor can be any device capable of measuring the concentration of glucose, including invasive, minimally invasive, and non-invasive sensing techniques ( Various techniques, including, for example, fluorescence monitoring, may be used to measure glucose to provide data indicating the glucose concentration at the host, eg, a data stream. The data stream can be the original data signal, which is interested in the health of the host, eg, user, patient, or nurse (eg, parent, relative, guardian, teacher, doctor, nurse, or host) Converted to a calibrated and / or filtered data stream used to provide glucose values to any other individual. Further, the continuous analyte sensor 10 may be implemented as at least one of the following types of sensors: an implantable glucose sensor, a transdermal glucose sensor implanted in a host vessel or outside the body, a subcutaneous sensor, a refillable. Subcutaneous sensor, intravascular sensor.

  In some implementations of FIG. 1, a continuous analyte sensor system 8 is used by DexCom, Inc. to continuously monitor host glucose levels. DexCom G4® Platinum glucose sensor and transmitter commercially available from

  FIG. 2 is a process flow diagram of a method for adjusting the interface type / style of physiological information (eg, graphs, sensor data display, buttons, alerts, default screens, and interaction preferences) based on behavior and / or situation information. It is. The adaptive reporting process 200 shown in FIG. 2 recognizes a pattern based on one or more inputs that may adaptively trigger support / partner mode. By recognizing the patient's situation, the adaptive reporting process 200 may cause the device to switch to an operating mode appropriate to the situation. The mode that is appropriate for the situation determines the length, amount, amount of ignored content, daily reset, and daily reset to present via the device output (eg, warnings, alarms, screens, information, etc.) , Can be adapted to take over skillfully without user effort. In some implementations, the adaptation may be based on a preset goal such as a target glucose reading.

  A process that provides automatic adaptation of user interface features (eg, settings or functions) based on behavior and / or situation information, depending on general-purpose devices for health care applications or a wide range of user preferences in a simple and intuitive manner The long-standing need to personalize health care devices intended for use is solved. That is, not all users have the same preferences when it comes to personalizing medical device, especially customer-driven medical device physiological information interface format / style (eg, user interface settings or functions for health care data) Absent. Some users may have technical knowledge and enjoy checking large amounts of health data, while others may prefer simpler interactions. Many users are in the middle, and their preferences can be influenced by contextual situations. Unfortunately, the creation of highly customizable devices is highly complex and vice versa and does not support full user coverage. There remains a need for an automatic and adaptable understanding of the behavior and status of customer driven devices that are highly intelligent and allow user interface adaptation. In one implementation, these needs include providing a report in a first manner / style (202), determining behavior or status information (204), comparing the behavior or status information to a goal or criteria. (206) achieved by adjusting the report format based on this comparison (208) and providing the report in an adjusted format (210), the device otherwise described herein. Of complex or comprehensive technologies, human behaviors (or situations), and health data that would seem extremely difficult, inefficient, and impossible for humans to do as possible with systems and methods It can be personalized to optimize health care and use efficiently, intuitively and intelligently without the need for understanding.

  “Adaptive reporting” generally updates or updates the reporting style or format (eg, of a human-detectable interface associated with a medical device or its data) based on received information so that functional characteristics are adjusted. Refers to the process, nature, or behavior that changes. In some implementations, adaptation is based on predictive reasoning derived from information gathered about the relevant user. Adaptive reporting systems and methods may be contrasted with reactive (or dynamic) reporting systems. A reactive or dynamic reporting system or method may provide a single reactive modulation in real time (eg, in response to a stimulus) based on a single event or selection, whereas an adaptive reporting system or method is , Predict events based on previous user behaviors or situations identified over time, and make progressive adjustments to settings or functionality based on them. One non-limiting advantage of an adaptive reporting system and method according to some implementations is to completely avoid the occurrence of undesirable events by predicting negative events and adjusting the system.

  The adaptive reporting process shown in FIG. 2 may be implemented in whole or in part using a continuous monitoring system such as the device shown and described in FIG. The adaptive reporting process 200 is a field programmable gate array or application specific integrated circuit or micro that is specifically configured to implement one or more aspects of the adaptive reporting process 200 described in connection with FIG. It can be implemented in hardware via a controller or the like. In general, reports can be provided (displayed) via a user interface (eg, a human detectable interface) such as a continuous monitoring device, patient record system, smartphone, or social media internet site.

  For ease of explanation, FIG. 2 is described with respect to glucose monitoring. The adaptive reporting process 200 begins at block 202 where glucose information is reported to the user / patient in a first manner or style. Not all users / patients like the common reporting style intuitively, nor can they recognize and deal with it. Furthermore, not all users / patients may be in a situation where they receive the same report at all times. For example, a younger patient who is habitually interacting with an electronic device may be adapted to a continuous monitoring system, unlike an older patient who is hardly interacting with an electronic device. As another example, when the user / patient is driving, it may be desirable to provide a brief information report that can be understood while operating the car. Similarly, stronger reporting may be desirable when the user / patient is watching television at home. Such variability affects patient behavior and may affect device utilization and / or results from using the device.

  In some implementations, the first style or style may be predetermined, such as during device manufacture. The first style or style may be selected so that basic information can be provided. In some implementations, a learning phase may be selected for the device. During the learning phase, the device may utilize a default first style or style. In some learning phases, it may be desirable to avoid reporting on some interactions / events or provide limited reporting on them until the learning phase expires. The duration of the learning phase may be based on the number of input information before deciding to turn on (or prompt) the feature. For example, a new device may not have information about the patient. In the learning phase, information about the patient, such as physiological readouts from the glucose sensor, activity information (eg, pedometer information), location information (eg, GPS coordinates), etc. can be received. When enough data is acquired to start the adaptation process, the learning phase may end.

  The reporting style or form may include audible feedback characteristics such as alarm frequency, tone, and volume. The style or style of the report will reflect visual characteristics such as trend graph resolution, brightness intensity, graph color, interface graphic, interface symbology (eg, for warnings), magnification level of information displayed, etc. May be included. The reporting style or style may include information display characteristics such as trend graph orientation, trend graph range, graph color scheme, dynamic trend graph, and the like. The reporting style or style includes the frequency of reporting, the number of specific types of alerts (eg, viable alerts, informational alerts, etc.), the amount of avatar assistance (eg, the number of interactive automation aids with animated character display), It may include vibration intensity and / or frequency, amount of data to display (eg, past 1 hour, 2 hours, etc.).

  Other report-related styles or forms that may be provided (adapted over time) include report default display, status-based report discretion, and reporting configuration (eg, device key when viewing a trend graph) By hitting, the trend graph temporarily expands to the trend line, or expands around the current glucose level / trend, glucose acceleration information (eg glucose rate is still accelerating, but not so rapidly) Not including signs that insulin has begun to act), predicted mode time, future mode time / input (eg, glucose, insulin, exercise, and other available input information, including future mode time or input A prediction may be generated, in some implementations, the prediction may be based on previous user data, thereby It is possible to improve the guess using the past input pattern to be similar).

  Alerts and / or alert settings that may be provided (adapted over time) include one of several high-level status categories in some implementations. For example, there can be three categories: information only, secure mode, and concentrated mode. In an information-only configuration, the system only disables all alarms and warnings and displays the information. In safe mode, the system sets alarms for severe hypoglycemia and hyperglycemia. In the intensive mode, the system is configured to operate under a more stringent blood glucose control target (i.e., 80-150 mg / dl). Although these settings are defaults, the system may adapt each individual setting (eg, warning level, volume, etc.) over time. These modes can also be selectively applied by the system based on the situation. For example, during a business meeting, an information-only mode may be desirable.

  Styles and / or styles may include screen order screens or menu items or hidden items, which may be adapted over time. Styles or modalities can also include the frequency and / or content of any information published to other devices or other persons such as doctors or nurses, which can also be adapted over time.

  At block 204, behavior and / or situation information regarding the user / patient is determined, as shown in FIG. FIG. 4 provides further details on how behavior and / or status inputs can be captured, tracked, determined, and shown, all of which are subroutines at block 204 of the adaptive reporting process 200. Can be applied as By identifying a particular situation or behavior during the natural use of the device, the system can adapt the reporting style of the user's situation or behavior. For example, the system identifies the patient as frustrated or confused by detecting that the patient is staring at the screen for a long time via eye tracking or other image or tactile detection Can do. As another example, a patient may be identified as satisfied based on facial pattern recognition obtained from image data. As a further example, the system may determine that the patient is in a particular social situation, such as a meeting at work or eating out with friends, based on GPS and / or calendar information. As yet another example, the system may determine that the patient is exercising or driving via input from an accelerometer. In each of these examples, the situation and behavior can be associated with physiological information without actually requiring the user to input information to be determined.

  Situation and behavior information may also be obtained by user input. For example, the user may be prompted to indirectly induce or adjust the behavior of the system by asking them to answer weighted questions. For example, “Do you want to tell people about yourself in steps 1-5?” “How often do you check your friends’ Facebook pages? ”“ How often do you check your time or body temperature? ” . Each question may be associated with one or more potential reporting styles or forms. For example, inform all or ask questions about Facebook can be used to establish the frequency and amount of data to report to others.

  Some implementations may use indirect questions to achieve more accurate adaptation, but in some implementations the system directly receives weighted preferences for various reporting styles or modalities Can be configured as follows. For example, the slider interface control can be calibrated from “little” to “as much as possible” for “how much feedback is needed”, “how much information do you want to share with friends or doctors”, etc. These direct questions, if present, can affect the frequency with which specific alerts are triggered. However, the user / patient is not directly asked whether to disable the alarm in this implementation.

  The determination of user / patient behavior and / or situation information is discussed in more detail below with reference to FIG. That is, status and / or behavior inputs may be captured as described in block 402, and behavior and / or status inputs may be tracked over time to collect a database of information as described in block 404. The input may be processed to determine behavior and / or situation information about the patient as described in block 406, based on which the indication of the situation and / or behavior information is an optional block. Optionally, as shown at 408, and / or status and / or behavior information is entered directly into block 204 as described herein.

  At block 206, behavior and / or situation information is compared to the goal / criteria. The goal / criteria can be an adaptive goal or a predetermined goal, as described in more detail in FIG. 5 (see, for example, blocks 502 and 510). Often, patient behavior and / or circumstances limit their ability to enjoy full benefit from physiological information, but by setting goals that take behavior and / or situation into account, useful physiological information has no effort. Can be personalized to meet the needs of the user without.

  Exemplary goals include the amount of interaction with the device, the amount of time within the target, the amount of time outside the target, the location of the device (eg, not leaving the device), data retention, calibration frequency, standard Deviations, pattern management (eg, number of days in and out of target), time spent on a particular screen, time spent low, time spent high, time with high rate of change, and rate of change The time when was low is included. The criteria may be set to determine whether the user meets the goal, for example, the criteria interacts with the monitoring system at least 10 times per day, is within the target range for at least 22 hours per day, 1 There may be no more than 2 hours per day out of target, the amount of data captured, the number of fingersticks entered, the number of menu selections and / or button clicks, etc. In general, the goal may be used to define by criteria (both of which may be adaptively modified over time as described with respect to FIGS. 5 and 6), which is determined at block 204. It should be understood that it can be compared with behavioral and / or situational information.

  In some exemplary embodiments, GPS input information can be used by the system to determine that the user has gone for a walk on the hill, which can be compared to a target / reference. Input information from the accelerometer can be used by the system to determine more exercise or more sleep, which can be compared to a target / reference. Inputs from the Internet of Things (IOT) (eg, machine-to-machine communication) are used by the system to indicate whether the user has not seen much TV or is buying healthy food from the refrigerator Can be determined and this can be compared to a target / reference. Using blood pressure data obtained from a blood pressure sensor, manually entered, or retrieved from a memory (eg, patient care record), it can be recognized that the associated user has better addressed the stress, , Can be compared to goals / references. The goals are described in more detail with reference to FIG.

  Incorporation of machine-to-machine communication provides multiple non-limiting benefits for effective treatment of patients with continuously monitored conditions, and data obtained from machine-to-machine communication is compared to goals / references Can be done. Devices can communicate with other networked devices, thereby expanding the types of data that can be provided and collected in the system. For example, the monitoring device may be in data communication with various devices at the patient's home, such as a television, refrigerator, temperature control system, computer, game console, security system, and the like. The monitoring device may be configured to automatically discover the nearest networked device that can provide data (where the goal / reference is based on proximity and the status information is the location / proximity of the device). Including neighboring devices). In some implementations, the monitoring device may be configured to connect with a predetermined set of devices. In such an implementation, additional security credentials may be provided to control access to the data. As two examples, data communication may be via a central network (eg, a local area home network) or a peer-to-peer mesh network.

  Consider the following implementation, including status information between machines. A networked sensor (eg, a GPS enabled device) may provide input to the system to determine when the user of the monitoring device is at home (ie, status information). The GPS can be a stand-alone navigation unit, included in a monitoring device, or included in another device configured to provide location information, such as a smartphone. Upon returning home, the light bulb may be connected to the network (ie, the criteria for using the light bulb include a GPS location indicating that the patient is at home). A light bulb can be used to provide reports to the user while at home. For example, the report may include transmitting a signal to a light bulb to change color when the user is high or low at home (eg, turns purple when high and orange when low). When the system receives input via the Internet of Things (IOT) indicating that the user's analyte level is below a threshold and does not recognize the alert, a hierarchy of alerts may be transmitted. First, a text message is sent to a predetermined follower in the vicinity (known by the GPS position). The follower may be notified based on their proximity to the person (eg, it is not necessary to notify a person determined to be in a different state). The front door is unlocked and nearby followers can enter the user's home (see, for example, Lockitron, a networked door lock manufactured by Apigy Inc.). If a nearby follower is not found, an email or text message can be issued for the emergency service. Entrance lights (also networked) turn pink, allowing emergency services to quickly identify which home needs to be found

  A follower may include all members of a user's community. For example, a follower network of all DexCom users can be created, whereby each user is identified as a follower of another person in the nearby DexCom network. By this method, a stranger can help a stranger if he is in the vicinity. Such a social system can allocate points to helping strangers and gain high status in the diabetic community. These dialogues can further promote cognition and help save lives. A follower network may be configured based on privacy preferences or other reporting criteria (eg, the type of report for use over the network, the amount of data to transmit, etc.).

  As described so far, the monitoring device provides messages to the device via machine-to-machine communication. In some implementations, communication may occur in the reverse direction, e.g., a severe low glucose condition with no signs of movement may activate the phone speaker, which can be assisted by a monitoring device. Enables a person to play a sound (eg, a phone call).

  At block 208, the manner in which information derived from the continuous monitor is reported is adjusted. The adjustment may be based on the comparison of block 206. For example, improvements in user interaction / display / alarm etc. can be identified by the system. Such identification can be preemptive and adaptive based on the pattern. Some exemplary adjustable reporting styles and styles are described with reference to block 202; however, any style or style (characteristic or feature) for reporting information will be understood by those skilled in the art. It should be understood that it can be adjusted by any means. The amount of repetitive and / or complete adjustment of the reporting style can be limited by boundaries that are predefined by the manufacturer and / or set by the user (eg, based on human factor studies). Iteratively try new reporting styles and see how user behavior responds or responds (eg, does not respond in certain situations such as conferences) and / or how Reporting styles can be personalized for the patient and adapted over time as changes with changes in the patient's environment, behavior, and / or situation. Can be. Adjustments in some implementations are automatic. In some implementations, adjustments can be made by recommendations, whereby one or more possible adjustments are provided and one or more indications of adjustments to apply are received.

  Reporting style or mode adjustments may include auditory feedback characteristics, such as changing (eg, increasing, decreasing, or other changes) the frequency, tone, and volume of alarms. Reporting style or style adjustments can be made visually, such as trend graph resolution, brightness intensity, graph color, interface iconography, interface symbology (eg, for warnings), magnification level of information displayed, etc. It may include property changes. Reporting style or style adjustments may include changes in information display characteristics such as trend graph orientation, trend graph range, graph color scheme, dynamic trend graph, and the like. Reporting style or style adjustments can include reporting frequency, number of specific types of alerts (eg, executable alerts, informational alerts, etc.), type or amount of avatar assistance (eg, interactive automation assistance with animated character display) Number), vibration intensity and / or frequency, amount of data to be displayed (eg, past 1 hour, 2 hours, etc.). Relevant styles or style adjustments can be used to change the default display of reports, the discretion of reporting based on the situation, the input configuration for the report (for example, by trending the trend graph by hitting the device key while viewing the trend graph) Expand to line or expand around current glucose level / trend), glucose acceleration information (eg, signs that insulin has begun to act, glucose rate is still accelerating but not so rapid) Predicted mode time (eg, longer or shorter predicted range), future mode time / input (eg, based on glucose, insulin, exercise, and other input information available, future mode time that can be generated Or in some implementations, the prediction may be based on previous user data. You can obtain, thereby improving the guess using past input pattern similar). Alerts and / or alert settings may be adjusted, such as one of a plurality of high level status categories, where the system may adjust the high level status categories over time and / or each Individual category settings (eg, warning level, volume, etc.) may be adapted. These modes can also be selectively applied by the system based on the situation. For example, during a business meeting, an information-only mode may be desirable. As another example, styles and / or style adjustments may include sorting screens or menu items or hidden items. Style or mode adjustments may also include changes in the frequency and / or content of any information published to other devices or other persons such as doctors or nurses, which also adapt over time Can be made.

  As another example adjustment, the received information may indicate that a response is not received at night as long as an alarm is provided at a certain volume. In this situation, the patient may be a sleepy person and the default alert volume during sleep time needs to be higher. As another example, the patient's spouse can be identified as a sleepless person (situation), so the alarm should only be vibration until it hits a certain glucose reading (eg, LOW55) ( Adjustment). As another situational indication or if the patient is identified as going for a walk (behavior / situation), the device is LOW55 within 1 hour when the user is seeking “diabetes vacation” for only 30 minutes. It can be determined that it does not want to be disturbed unless it can be hit (adaptation). If the user is determined to be out most of the time (situation), environmental adjustments may also be provided, such as a brighter contrast may be used for the trend screen display. Other adjustments include providing a higher level of discretion (adjustment) when detecting the location of a work meeting, users who are determined to be overwhelmed by data, or newly diagnosed users Providing a high level of reporting. In some implementations, the adjustment may feature a progressive scheme that, upon completing certain criteria, allows the reporting style to be adapted to the next level of sophistication. Adjustments are applied continuously (after adjustment until the next adjustment) and / or depending on the behavior or situation specified at any particular time (depending on the real-time situation / behavior) (Regulation profile) may provide a series of adaptations.

  Further examples of adjustments include changing the icons and / or warning symbols that reflect real-time data. For example, when a drop alarm is activated, the icon on the device for the “drop alarm” will show an image of a trend graph with the actual data points falling from the glucose reading instead of the general display of the drop glucose diagram. Can show.

  Adapted reporting organization can include identifying a reporting hierarchy that starts with basic reporting and evolves into more important / complex reporting. For example, for a deep sleep patient, the sensor input may indicate that the user is not aware of a low glucose alert triggered at night. In a diabetic situation, this can be caused by the person sleeping or, more importantly, by the person entering a dangerously degraded state and unable to respond. obtain. The report can be adapted to provide a loud alarm first in the evening hours and gradually increase the volume over time. Hierarchies also provide alerts using alternative reporting means such as ultimate alerts defined as a user's home call, neighbor call, and emergency service call (eg, 911). , Threshold points may be included.

  Based at least in part on the collected situational and behavioral information along with the monitored physiological characteristics, the system is configured to evaluate over time how the patient's condition behaves and responds. The For example, the weather (situation) and the patient's exercise regimen (behavior) can combine to cause a drop in glucose. Although patients may not identify this correlation, it can be expected that a decline may occur based on past events through analysis of the collected information. In such an implementation, the monitor may take aggressive steps to maintain patient levels such as medication administration, increased monitoring frequency, display of warning messages, and the like.

  Analysis of specific characteristics related to the patient's condition may be useful in identifying other trends or anomalies related to the specific patient. For example, if an atypical pattern is detected, other problems can be evaluated as possible causes of this variation. Such problems include food allergies, celiac disease, gastric insufficiency, etc., which can be identified based on situation / behavior information. This past knowledge informs you of guidance / advice to best respond to a particular situation or trend. For example, potential rebound degradation can be detected as occurring periodically. The system can be adapted to automatically alert the patient of the time to eat to best avoid both low (blood glucose) and high due to rebound (blood glucose). Trends can also be categorized based on low / high risk, rebound, etc., and the frequency of reporting is adapted as the risk of glucose fluctuations changes.

  Changes in reporting characteristics are not necessarily included in the same category as the behavior information. For example, an increase in user interaction may trigger a change in the interface, and an increase in hypoglycemia may also trigger a change in the interface. In some implementations, one type of behavior information can be used to adjust multiple reporting characteristics. Similarly, behavior information of multiple elements can be used to adjust a single reporting characteristic.

  The situation / behavior information can be used to configure general device characteristics. For example, the general device user interface of graphs, display of sensor data, buttons, alarms, default screens, and interaction preferences can be reconfigured. In some implementations, it may be desirable to interact with the user through the game. In such a mode, a reward can be provided when the desired behavior is detected. In such an implementation, the types of rewards provided, the amount of rewards, and the frequency of rewards granted may be adjusted based on the situation / behavior information.

  Discretion may be desired for a particular user. As a means of ensuring discretion, a first level alarm is provided that only vibrates without activating the screen, or otherwise “awakens” the characteristics of the monitoring device. Can be done. In such an implementation, the monitoring device may be released from the stopped state when a button press operation is detected. The button pressing operation may include a defined series of buttons that allow for an inadvertent release of the stop state through “pocket push”, for example. This can also provide a certain level of security to the device by identifying the specially configured suspended state release input to the monitoring device.

  At block 210, a report is provided based on the identified adjustment. As described, altering the reporting of glucose information based on personalized interactions increases usage, responds to provided information and alerts, and ultimately improves results (eg, health) Can help. User behavior and / or status can be tracked and their responses can be determined. Additional adjustments may be identified through subsequent iterations of the adaptive reporting process 200. The reporting format and / or goal / criteria adjustment is used to adapt the reporting format so that interaction with physiological information is personalized with respect to a particular person, a particular situation, and a particular time.

  The provided reporting is a further adaptation that can be made by the system based on the obtained status and / or behavior information. For example, the report may be directed to another device (eg, an inter-machine device) or human use (eg, email, text information). Examples of reporting destinations include insulin pumps, networked storage devices (eg cloud storage), social media communities, Smart TV, computers or applications running on computers (eg widgets), phones, watches , Doctors or other caregivers, PCS (patient customer support) teams, parents, loved ones, followers (eg, people whose continuous glucose monitoring (CGM) patients “share” their CGM data), activity tracking devices , Mobile phones, rings, pendants, smart refrigerators, medical systems such as medical instruments or hospital networks, phones where rewards are included as game points / currencies (eg credits that can be used in games to acquire additional features) And the like of the game or application.

  Providing the report at block 210 may include providing positive feedback to the user. Determining how the patient responds to positive feedback (eg, positive feedback is more successful than when there is little or no positive feedback) is the situation / behavior information As a patient input. The system can be configured to use this information to adapt the goals and / or additional resulting reporting formats, such as those described with reference to block 208. Feedback can be organized at the individual patient level. Feedback may be provided to groups or teams of users so that relationships or team-based / connections or partnerships with others are motivated.

  Devices that include such feedback can improve confidence in diabetic patients through positive reinforcement. Providing a report at block 210 may include identifying a positive trend or behavior and providing this information in the report. For example, a simple goal may be associated with a user, such as wearing a sensor for two days or checking the number of monitors five times a day. Such simple goals can be organized in a hierarchy so that after the easier goals are first achieved, they will “progress” to the next level of complexity.

  The system may identify and reward reward events patterns such as improvements or good monitoring reports. The reward may be known to the patient in advance or may be a surprise reward. The reward may include a “bragging” reward associated with social media, such as an avatar, icon, etc. that is restricted in access.

  Providing reports may further include goals and indicators of their achievement. Goals can be user defined (eg, by patient, physician, parent) or predetermined (eg, a library of diabetic patient goals). Users get rewards and badges when they achieve these goals. The badge allows the user to advance the rank of CGM knowledge and go to the next step, thus enhancing success. The collected information regarding goal achievement may provide data regarding which therapeutic interventions are more effective than others.

  Other examples of feedback that may be provided at block 210 include notification of a time period during which the system does not detect a target analyte level below a threshold. Such a period may be referred to as a “day without hits”. Other examples of feedback give up to schedule a visit to a doctor or other consultation (eg ophthalmologist, dentist, etc.) that helps manage the overall picture of living with diabetes Is. On days when glucose control fails to meet the target criteria / threshold, feedback can be provided to cheer or motivate the patient. Such a day may be referred to as a “bad” day. Target criteria or thresholds for “no hit days” or “bad days” can be preset, default, user-defined, or adapted over time). Examples of “bad” day feedback may include the selection of messages that give hope by the system (eg, it ’s okay because everyone has a bad day). In some implementations, the message may include patient-specific information such as “Remember X days when there was no hit. Turn tomorrow, take a break, and try again!” . In this way, patients may not be positive for all their experiences with diabetes, but despite their hard work, they must wake up and do the same with the same constant effort. Even if there is a “bad” day, you can realize that it is important to improve your confidence by recognizing that there is / can be a good day ahead.

  Based on the initial processing, additional information or input may be identified as useful for further adaptation. For example, if no location information is identified at block 210 in adaptive reporting process 200, a request to enable GPS or provide GPS input may be included. For the received input, the configuration of the sensor providing the input can be evaluated and suggested changes can be proposed. For example, the sensor insertion position can affect the monitoring process. Having identified fluctuations in the data received from the inserted sensor, sensor adjustment may be proposed.

  As an example implementation, after providing a report (block 202), the system determines that the user has not calibrated the device for several days. This determination is based on data received from the device, which is stored each time the device is calibrated. The last calibrated date can be stored in memory and compared with the current date (to determine behavior information at block 204). If the number of days exceeds the threshold, the absence of calibration may be identified (by comparing the behavior information with the target / reference at block 206). Because the accuracy of the report can be affected by calibration, identifying this behavior allows the system to adapt the report to include feedback or other content (at block 208). Feedback may be identified from a catalog of feedback items categorized by behavior and / or situation. The system can identify static items (eg, text messages regarding the importance of calibration) for inclusion in the report. The system can identify dynamic items. Dynamic items may include user specific information, such as the number of days since the last calibration. The dynamically included information may be selected based on received behavior and / or situation information regarding the user. The system can identify interactive items. An interactive item includes an input request (prompt) for the user to provide a response. The response can be in a free form (eg, a free form question in which textual information is provided in the response) or a restricted form (eg, multiple choice, sliding scale, valid value). Once included in the report (at block 210), the feedback can be presented in the report or via a message interface (eg, notification icon, text message, email) that is included in the device. If the feedback includes interactive items, the device receives user input and transmits a response to the system for further processing. Further processing may include storing a response, extracting a natural language of keywords from the response, identifying subsequent feedback items, and the like.

  While the method for adjusting the interface type / style of physiological information based on behavior and / or situation information in FIG. 2 has been described, certain embodiments incorporating the described features may be an innovative aspect of the method. It can function to further emphasize.

  In another example, the monitor reports CGM data to the user with a high sensitivity alert (at block 202). The system determines that the user exhibits a pattern that ignores the alarm (behavior is determined at block 204). The determination is based on an analysis of the frequency of interaction with the CGM display and an alarm condition that lasts for more than an hour on average. The system can identify the user's goal from a library of predetermined goals based on the identified behavior pattern or situation information. The goal may be to not experience an alarm condition that lasts on average for more than one hour (pattern) and / or interact with the device at least twice during an alarm condition that lasts for more than one hour (block 206). ). To help achieve this goal, the system may further identify adaptations to the reporting style, such as sound changes, volume increases, and / or alarm frequency increases (block 208). With the adapted alert type, the user continues to use the monitor without necessarily performing the analysis and adjustment specified by the system (block 210). In some implementations, adaptation can be verified through received user input (eg, recognize changes and enable control).

  Further details regarding alarms, such as alarm settings, alarm conditions, alarm criteria, are provided in US patent application Ser. No. 13/742, filed Jan. 16, entitled “Systems and Methods for Providing Sensitive and Specific Alarms”. 694, the entire disclosure of which is expressly incorporated herein by reference. The alarms, conditions, and / or criteria described can be adapted using the systems and methods discussed herein.

  In another example, the monitor provides personalized assistance regarding maintaining the analyte level within the target range. The system recognizes that only the user uses a particular system interface (after reporting at block 202, behavior is determined based on the screen view at block 204 and compared to the criteria at block 206. ). The system automatically prioritizes menus / screens associated with users under good glucose control (e.g., the average reading over a period of time is within a threshold amount) in block 208 to a predetermined scheme. Adapt. Adaptation (208) may include storing a flag indicating that a particular menu item is hidden (210). Adaptation (208) generates a display so that the adjusted list is characterized by items with high usage at the top of the list and items with low use at the bottom of the list. Adjusting the list of menu items used to be included can be included. If the user is not under good glucose management, the system can be adapted (at 208) to provide advice (at 21) on other interfaces that can be used to improve control. This advice may include informational messages, other product promotions, or additional behavior / situation input that may be useful to incorporate into the surveillance system.

  Where advice / guidance is provided, the information provided may be based on a known best practice that corrects / avoids the tendency to worsen or more dangerous glucose fluctuations. Information can be selected and / or users or similar populations can refer to historical data as well. The information provided can include multimedia information, text information, or auditory information. Information is stored in a database and may be associated with one or more situations, behaviors, or conditions to be monitored.

  In some exemplary implementations, the system can determine (at 204) a behavior that the patient is not calibrating at 206 at a suggested interval (eg, every 12 hours). In some cases, it can be determined that the patient has completely omitted calibration. In order to reduce the amount of time that CGM prompts for calibration, this user report may be inaccurate because the value being monitored is not calibrated after missing a certain number of calibration opportunities. Adapted to provide a message that there is (at 208).

  In some exemplary implementations, the system may determine that the patient has not set a rising warning or a falling warning. One of the benefits of continuous monitoring is that patients change their behavior based on past trends. For such patients, the monitor may determine whether the person is in a high or low range for too long. The monitor then provides a report informing the patient that blood glucose is very high (eg, 400 mg / dL) or low (eg, 60 mg / dL) at a certain time of day (E.g. once every 3-4 days). This is just one specific example of warning and adaptation. The system may be configured to identify various other patterns and apply one or more adaptations as needed.

  In some exemplary implementations, the system may provide a predetermined set of reporting profiles. A given user may be associated with one of the profiles based on the received situation / behavior information (eg, user preferences about how the system should behave). For example, an unnecessarily worried user may always want to know what state they are in, but does not want loud sound warnings and may tend to prefer frequent warnings and pleasant sounds. If the user does not respond to the warning or does not look at the screen very often, the system can determine its behavior and change the warning setting as needed (ie, change the threshold from 80 to 70, Or vice versa). As another example, if a user changes from normal to mute each morning at a specific time, the system may be adapted to automatically make such adjustments based on the user's historical information.

  In some exemplary implementations, the system transitions from 100 mg / dL to 60 mg / dL or 200 mg / dL or 300 mg / dL based on time of day, day of week, or using other external sensor inputs. Can be adapted based on the determination of how long it typically takes. This prediction of risk estimation may be based on an understanding of insulin, exercise, and time / day of the week. The goal of risk estimation is to determine whether an individual is at risk (or has a higher probability) of becoming hypoglycemic at a particular night. Whether to become hypoglycemic depends on a number of parameters such as food, exercise in the last 24/48 hours, insulin on board, hormonal changes, and stress.

  To perform the adaptation, a probability distribution of these parameters is provided to the individual. For example, a hypoglycemic probability distribution based on one or more information of food, exercise, insulin on board, hormonal changes, and stress can be provided in advance and / or a particular patient based on a pattern over time Can be adapted to. Probability distributions can be provided for other parameters / information as well. A “likelihood” estimate can then be generated by the system based on the probability distribution to determine if a person has low or high likelihood of becoming hypoglycemic. For example, if the person is normal and all the above parameters / information are near the mean (eg, within the distribution), the likelihood of being normal (the product of all probabilities) is high. If one or more parameters deviate from the mean, the product deviates from the likelihood of being normal.

In one exemplary implementation, the parameters are:
1. Food consumed in the last 4 hours: N (mu1, sd1), peak probability when the consumed food is in mu1 is 0.1 (eg, 100 g carbohydrate).
2. Insulin onboard for the past 8 hours: N (mu2, sd2), peak probability is 0.1 when insulin is mu2 (eg, 20 units).
3. Exercise for the past 4 hours: N (mu3, sd3), peak probability is 0.1 when exercise is mu3 (eg, intense exercise for 2 hours).

Here it is assumed that these parameters are normally distributed with the indicated mean and standard deviation. These values and probabilities are the person's normal level and are considered normal at this level (ie glucose is within the normal range, ie, 70-180 mg / dL). The likelihood of observing data when this person is normal on a particular day is defined in Equation 1 based on the example parameters described above.
L (data / normal) = Prob (food) × Prob (insulin) × Prob (exercise) (1)

  If everything is average (ie normal), the likelihood is highest, in this example 0.1 × 0.1 × 0.1 = 0.001. Suppose that the system determines that the person has consumed a significantly smaller amount of food on a particular day (eg, 10 grams of carbohydrates). In this case, the probability value of 10 g in his distribution is much smaller than 0.1. For example, this can be 0.01. If this happens and he does the same amount of exercise and takes the same insulin, then the likelihood of becoming normal is now 10 times lower, or alternatively, 10 times more likely to be hypoglycemia. Get higher.

  As described, the system adapts the model to the normal behavior of a person. If the input indicates a change, the system generates an estimate as to how the change affects the risk of hypoglycemia. For example, for food, mu1 is a typical carbohydrate consumed during a meal (eg, 50 g), sd1 is a meal-to-meal variation (ie, 45 g, sometimes 55 g, etc.) ).

  FIG. 3 shows a plot of a histogram (or distribution) of carbohydrates contained in a meal over a 30 day period. The histogram shown shows the mean (mu1) and standard deviation (sd1). The information in this graph can be used to adapt the above report. For example, the warning glucose threshold may be adjusted if it is determined that the patient is in an Italian restaurant.

  Another example is to adjust menu items based on the benefit to the patient in managing the disease. For example, the system detects how often a user accesses a particular menu item. As used herein, a menu item generally refers to a display selection or user interface control that provides information to a user of the device. Menu items can be fixed based on the frequency of access considered by the system developer. However, as noted above, the recognition of useful items can vary from patient to patient, and the determined menu format may not be useful for disease management for all people in the same manner. Therefore, this system can specify the access frequency of each menu item. Based on the identified frequency, the display of menu items may be adjusted. Adjustments include reordering menu items, hiding menu items, increasing the display to make it more or less noticeable (eg font size), and associating “hot keys” with menu items Etc. may be included. Depending on the features described, the priority and display characteristics of the menu items can be adapted.

  As described, the system includes a set of reporting profiles that define alert behavior. These defined profiles are based on previously acquired information on different profiles that on average match people's preferences. By observing the actual behavior of a particular user when the user begins to use the system, the system can adapt the profile to meet that user's uniqueness. Adaptation may suggest a new profile if the user has specified a profile preference but has selected a profile that does not fit the specified situation / behavior detected by the system. The system may then apply a new adapted profile that better matches the user.

  FIG. 4 is a process flow diagram of a method for determining patient behavior and / or status information. It may be desirable for the user to capture input without extra effort / interaction. By configuring the system to capture behavior and / or situation information from various inputs associated with the user's behavior and / or situation in the device usage environment, the user is burdened with explicitly providing such information. Without spending time, the user is more likely to use the device and benefit from it. For example, a user may pass through a communication hub installed at home or in the car, thereby synchronizing data input to the cloud / server or the like. The system can be configured to organize data and learn and organize individual behavior. Goals or criteria can be identified based on the data. Information may be sent back to the device at user-specified intervals, daily, weekly, monthly, etc.

  The process 400 shown in FIG. 4 may be implemented using, in whole or in part, a continuous monitoring system such as the device shown and described in FIG. The behavior and / or status information determination process 400 may be implemented as a server process in data communication with a continuous monitoring device. The behavior and / or situation information determination process 400 is a field programmable gate array or specially configured to implement one or more aspects of the behavior and / or situation information determination process 400 described in FIG. It can be implemented in hardware via an application specific integrated circuit or a microcontroller.

  The process of determining behavior and / or situation information uniquely personalizes a general purpose device for health care applications or a health care device intended for use with a wide range of user preferences in a simple and intuitive manner. Identify information that can help solve long-term needs. That is, not all users have the same preferences when it comes to personalizing medical devices, particularly customer-driven medical devices. Some users have technical knowledge and enjoy checking large amounts of health data, while others prefer simpler interactions. Many are in the middle, and their preferences can be influenced by the context of the dialogue. Unfortunately, the creation of highly customizable devices is highly complex and vice versa and does not support full user coverage. There remains a need for an automatic and adaptive understanding of the behavior and status of customer-driven devices that are highly intelligent and allow for simplicity of use. In one implementation, these needs include capturing situation and / or behavior input (402), tracking behavior and / or situation input over time and collecting a database of information (404), Processing to determine behavior and / or situation information about the patient (406), optionally providing an indication of situation and / or behavior information (408), and / or the adaptive process described herein Optionally provided with behavior and / or status information (ie, block 204 of process 200, block 504 of process 500, or block 602 or process 600), the device What humans do as possible by the systems and methods described in the specification Efficient, intuitive, and knowledge without the need to understand complex or comprehensive technologies, human behavior (or situations), and health data that would be difficult, inefficient, and impossible Can be personalized for personal health care and use optimization.

  At block 402, status and / or behavior inputs are captured. The input can be discovered or registered, for example, as described above. The behavior input information can be obtained via the system. Behavior inputs include the amount of interaction, glucose warning / alarm status, sensor data, number of screen hits, alarm analysis, events (eg, characteristics associated with user response, time to response, blood glucose management associated with response, User feedback related to alarms, not recognizing warnings / alarms within x minutes, time to recognize warnings / alarms, time in warning state), diabetes management data (eg CGM data, insulin pump data, insulin sensitivity) , Pattern, activity data, calorie data), free fatty acid, heart rate during exercise, IgG-antigliadin, stress level from skin patch sensor (sweat / sweat), free amino acids, troponin, ketone, ketone, adipanectin, Troponin, sweating, body temperature, etc. may be included. The input may be provided by a sensor that is in data communication with the monitoring device. In some implementations, the information may be obtained through intermediate layer values such as remote data storage.

  Context information that can be provided to the system as input includes human biology, location, sensing status (eg, lighting, sound level), and environmental data (eg, weather, temperature, humidity, barometric pressure). Input may be received via peer-to-peer or mesh networks via machine-to-machine communication as described above. The situation information may include routine information from the calendaring application, which may vary from weekdays to weekends. The status information may include the frequency of touching or grabbing the monitoring device, even when not interacting based on the sensed movement of the device (eg, accelerometer or camera sensor). The photo may provide status information. For example, one or more pictures of glucose meter readings, insulin pen or pump IOB, location (eg, gym, park, home, Italian restaurant), or meal may be used to provide status information. The photos can be processed, for example, to identify the caloric intake of the meal shown in the photos. The type of insulin used can also be provided to the monitoring device as an input useful for adapting the system. The situation can also be provided by the basis or bolus settings provided to or determined by the monitoring device.

  Other inputs to the adaptation process include exercise information from fit bikes, glucose sensor information from blood glucose (BG) meters or CGM, insulin delivery from insulin delivery devices, device on-board calculations, and Contains information provided or calculated by other devices.

  Hydration, heart rate, target heart rate, internal temperature, external temperature, external humidity, internal analyte, hydration input, power output (cycling), sweat rate, pace, adrenaline level, stress, disease / disease, metabolism / Calorie consumption rate, lipolysis rate, current weight, BMI, desired weight, target daily calories (consumption), target daily calories (burning), location, favorite food, level of effort, It is an additional example of a situation / behavior input.

  For any of the behavior or status inputs referenced above, the system can be configured to receive and / or generate an analytical metric based on the inputs. For example, a composite value may be generated based on glucose level, temperature, and time to generate a user index value.

  Because the system can provide goals, behavior information can include detected improvements or success rates for goals / criteria. People who review past glucose data have been shown to have better diabetes management. The information may include a time stamp for identifying how often past glucose data is to be confirmed.

  The first input at block 402 is internal (eg, within the monitoring device), such as sensor measurements, internal calculated values, and / or other information provided by the patient at the initial query stage or known to the system. It can be derived data. For example, information regarding the user interaction and the results of the response (short term and / or long term) may be identified.

  The initial input can be used to generate the adaptation / advice / teaching confidence that the system generates for the user. Confidence may allow a user to specify a level of “ambiguous” adaptation, advice, and guidance that they are willing to accept. One means by which an input can be used by the system to generate confidence is how much the user trusts the system that can identify and adjust its operation based on received behavior, status, and physiological information. It is to identify whether or not. For example, one person fully trusts the system and can automatically adapt over time without any user intervention, while another person trusts the system and is able to For example, the menu item) may be adapted but may not be trusted to adjust the analyte threshold without approval.

  In some implementations, each identified adaptation can be associated with a confidence score. The confidence score is the amount of data received from the user included in the adaptation decision, the amount of data received from the device included in the adaptation decision, the user community or device included in the adaptation decision May be based on one or more of the amount of data received from a user with similar health concerns to other users, or a characteristic indicative of the sophistication of the user's usage. These quantities can be compared to respective threshold values to determine a relative confidence score for the proposed adaptation. Thus, the more data that is available, the higher the reliability of adaptation.

  Based on the confidence score, and in some implementations, based on the user confidence level (eg, system confidence level), the system (in adaptive reporting process 200, adaptive goal setting process 500, or adaptive guidance). It may be configured to automatically apply the adaptation (within process 600), apply the adaptation after confirmation, or apply no adaptation at all.

  At block 404, behavior and / or status inputs are tracked over time to build a status database (build an input record). The system may periodically store pre-specified inputs, where user-specific pre-specified inputs are created. By tracking over time, the pattern can be estimated. For example, behavior information is meaningful when a history of a particular usage pattern is provided over time. Similarly, status information can be tracked and associated with time (eg, a user is typically at school from 9 am to 3 pm).

  In some implementations, the tracked data can be collected in a specially adapted database on the device. In some implementations, the storage device may be in data communication with a device (eg, a cloud or other device (eg, accelerometer, sleep tracking device)). Collection may be directly from the sensor or via an intermediate module such as a calendar.

  The collected information may include information collected by the user under the same conditions as the user of the device. For example, for a patient query, the system gives x% weight to the user's past data and y% weight to other users under the same conditions, resulting in a sum of x and y of 100. % Is configured to respond using a weighted response. Depending on the user's own past reference and learning, and how to compare to a larger population, how the trend or health plan is progressing, and what therapeutic to resolve the condition or maintain the desired condition Intervention / action / step is possible and useful for adaptive processes (within adaptive reporting process 200, adaptive goal setting process, or adaptive teaching process 600) to better identify the most successful Provide input to get.

  At block 406, the input is processed to determine behavior and / or situation information about the patient. Information can be collected in records about the patient. Processing can be periodic, such as according to a schedule, or event driven (eg, upon receipt of new input data, during idle system time). The system is configured to identify patterns of behavioral or situational information (eg, user interaction with a physiological information display). The identification may be based on recognition of a predetermined pattern of input data (eg, one or more values or ranges of values associated with a behavior or state). For example, if the input is an accelerometer and the detected speed is 70 mph, the speed input information may be associated with driving behavior. In some implementations, the system may include or communicate with an artificial intelligence module that is adapted to estimate situation and / or behavior information associated with the patient. The generated patient information may be used to further adapt the device, such as those described above with respect to block 204 of adaptive reporting process 200, block 504 of adaptive goal setting process 500, and / or block 602 of adaptive teaching process 600. Can be used as status and / or behavior information.

  The example method shown in FIG. 4 includes block 408, which provides an indication of the identified situation and / or behavior information. Block 408 may be omitted in some implementations. Some information may be estimated or inferred automatically, and block 408 functions in part as a “justification check” for the information and adaptations based thereon. By providing an indicator of identified information, a user (eg, patient, doctor, nurse, etc.) can provide some feedback regarding the identified information. For example, the indicators may be provided in the form of a question with a question or response selection on the user interface or a report with a free form response. Exemplary questions include "Is this correct?" "Should I take action on this information?"

  In some implementations, the indication may be transmitted to another device, such as an insulin pump, medical record, or other system included in the patient's care plan. By transmitting the indicators, these systems (or monitoring systems) better estimate and understand their capabilities, good estimation / determination / intuition, inconsistent estimation / determination / intuition, or poor estimation. / Helps to adapt operating characteristics based on decision / intuition. Monitoring devices can even be configured to respond with teaching / learning to help other devices improve their estimation / determination / intuition.

  As an example, an interactive avatar displayed on the device may display an input request to the user asking, “Do you stay at home?” Or “Do you want to change your alarm settings when you are at home?”. Based on the response, the device will determine which control algorithm is activated, which basic profile to start with, where to send alerts, and when to open the loop of the closed loop control system (e.g., change or half Insulin pumps may be informed about situations or behaviors that may affect, for example, adjusting to include a transition to a closed or non-closed state. The device may be configured to transmit this information to a cloud or electronic medical record for collection in a database (preferably in a pre-specified form).

  Providing the indicators may include speech recognition, verbal queuing, and / or natural language processing. For example, the response to the indicator may be delayed “I think so”. Such indecision can be identified based on the waveform of the received speech. This indecision can be used to not take into account the information shown. For example, if the identified behavior is “fishing on ice” and the received response is a slow “I think so”, the system is configured to consider this behavior for limited purposes only. Can be done.

  As described, when providing information, further requests and / or processing of additional information / input from the user may be based on a data processing / feedback loop. This allows the adaptation process to operate with the information provided and to obtain inputs that are likely to result in adaptations that are objectionable for the user.

  The system can be configured to remind the user that reviewing historical data is an important part of diabetes management. The reminder may be included as a periodic display message via the device. In some implementations, reminders are combined with other behavior / situation pattern recognition to generate messages for display to the user regarding past data.

  Consider the following example, including the embodiment of FIG. The user enters data into the personal calendar, which is registered to communicate the calendar data to the monitoring device. For example, when analyzing calendar data via a keyword search, the system identifies that the user's future events include exercises such as scheduled yoga classes. The monitoring system can see that this class occurs repeatedly every week. Therefore, the surveillance system adapts to exercise patterns and makes recommendations such as “If you plan to exercise within one hour, will you start a temporary basal speed now?” One hour before the scheduled class. Can be done. As another recommendation, the system may present a message to the user such as “Think about eating a snack now if you plan to exercise within an hour”. Messages can be selected based on previous exercise patterns from similar activities. In some implementations, the input information may be obtained from a social media calendar or event planning system, such as a Facebook ™ event or an Evite ™ invitation.

  By determining a future event / behavior / situation (within process 400), a corresponding adaptation may be provided. For example, if activities such as sustained exercise, long bicycles, etc. are identified, recommendations should be made to identify appropriate suggestions and the time to provide suggestions based on the events involved and other patient details. Can be queried. For example, the system may identify reminders for patients who take a small snack midway to prevent hypoglycemia and / or nutrition. The proposal may also include a snack that may be based on information from the smart refrigerator regarding the available food items in the refrigerator.

  The monitoring device may be configured to identify location information. The location information may be obtained directly from the location device that is included in or in data communication with the monitoring device. Over time, patient location information can be used to help understand life patterns and possibly even activities. For example, the location may be geocoded to identify a business that is performed at a given location (eg, gym, Italian restaurant, grocery store, movie theater, etc.). The location information may be utilized by an adaptive reporting process (200), an adaptive goal setting process (500), and / or an adaptive guidance process (600) to determine location-based adaptation and / or goals.

  Additional input may include audio input such as user records. The monitoring system may be configured to identify stress, panic, or anger by analyzing recordings (eg, conversation wavelength, tempo, pitch, volume, duration). Stress, panic, and anger can also be identified based on physical behavior. In general, the more cheerful a person is, the higher the degree of excitement. Thus, motion information can be captured by the device (eg, from an accelerometer) and compared to an activity threshold. The activity threshold can be a standard threshold or can be adapted to the patient. If the detected activity level exceeds a threshold, the patient is highly excited and can therefore be identified as being stressed, panicking, or angry. The threshold can be calibrated for each of these three emotions (or other emotions).

  FIG. 5 is a process flow diagram of a method for determining goals or criteria used in one or more aspects described. The process adaptive goal setting process 500 shown in FIG. 5 may be implemented in whole or in part using a continuous monitoring system such as the device shown and described in FIG. The adaptive goal setting process 500 may be implemented as a server process that is in data communication with a continuous monitoring device. The adaptive targeting process 500 is via a field programmable gate array or application specific integrated circuit or microcontroller, etc. that is specifically configured to implement one or more aspects of the adaptive targeting process 500 described. Can be implemented in hardware. The goal or criteria determined by the adaptive goal setting process 500 is the use of one or more of the described processes, such as block 206 of the adaptive reporting process 200 and / or block 602 of the adaptive teaching process 600. Can be provided for.

  Health intended for use in a general purpose device or for a wide range of user preferences for health care applications in a simple and intuitive manner with a process that provides automatic adaptation of goals or criteria based on behavior and / or situational information The long-standing need to personalize managed devices can be solved. That is, not all users have the same preferences when it comes to personalizing physiological information goals or criteria for medical devices, particularly customer-driven medical devices. Some users are particularly motivated and can achieve certain goals quickly, while others can be more time consuming. Many users are in the middle, and their preferences can be influenced by contextual situations. Unfortunately, the creation of highly customizable devices is highly complex and vice versa and does not support full user coverage. There remains a need for an automatic and adaptable understanding of the behavior and status of customer-driven devices that are highly intelligent and allow the adaptation of goals and standards. In one implementation, these needs include providing a predetermined goal to the user (502), determining user behavior or status information (504), optional other user ongoing behavior or status information. The device is satisfied by obtaining (506), adapting the goal to the user and / or optionally other users (508), and providing an adapted goal or criterion (510) A complex or comprehensive technology, human behavior that would otherwise seem extremely difficult, inefficient, and impossible for humans to do with the systems and methods described herein. (Or situation) and can be personalized to optimize health care and use efficiently, intuitively and intelligently without the need to understand health data .

  “Adaptive goal setting” generally refers to the process, nature, or act of updating or changing a goal or criterion based on received information such that the goal or criterion is adjusted. In some implementations, adaptation is based on predictive reasoning derived from information gathered about the relevant user. An adaptive targeting system or method may be contrasted with a reactive targeting system or method. A reactive targeting system or method may provide a single reactive adjustment in real time based on a single event or selection (eg, in response to a stimulus), while an adaptive targeting system or method includes: Predict events based on previous user behavior or situations identified over time, and make progressive adjustments to goals or criteria based on that.

  A goal generally refers to a desired result, such as a more frequent check of past data. For each goal, there may be one or more criteria that indicate whether the goal has been achieved. For example, if the goal is to increase the frequency of past data checks, the criteria may include the number of desired checks per time unit and the number of previous time unit checks. A goal may specify a relationship between criteria. For example, the goal may include an indication that the number of previous time unit checks must be greater than or equal to the desired number of checks per time unit. More complex relationships can be defined in the goal. The goals can be organized hierarchically such that higher level goals cannot be achieved without first meeting lower level goals.

  Examples of goals include a goal focused on setting up the system, a goal to set a threshold, a sensor wear time goal, a sensor session goal (e.g., first complete the sensor session, Use), device calibration targets, alarm recognition targets. Some goals may be selectable goals that correlate with other status inputs. For example, it should not drop during exercise. The goal can be situational sensitivity. For example, the goal may be based on the detected location. For example, do n’t drop when you ’re in the gym. Further examples of goals include insertion goals such as how to use the applicator, hand washing, sensor placement, sensor session initiation. Retrieval / discard goals, such as how to maximize session data and sensor discard methods, can be established and monitored by the system. Still further examples of goals include data goals (eg, how to read data, how to set alerts), community goals (eg, how to provide / provide support to others) ), Daily goals (eg how to deal with eating behavior, how to deal with exercise behavior, sleep behavior), device maintenance goals-how to clean the transmitter, how to receive How to charge the instrument, how to customize the transmitter, how to change alarms, how to calibrate), processing targets (eg how to calculate carbohydrates, target range) Or whether to calculate insulin onboard).

  Other examples of goals include entering specific goals, such as for pediatric patients transitioning from managing diabetes with parents to achieve a better level of self-management in preparation for self-help . In order to help patients actually use the system and make diabetes management their own, the use of carbohydrate counting goals or photographic software for counting carbohydrates can be identified to these patients. Because young users respond more aggressively to rewards, the adaptation process also includes providing rewards for positive behavior. Furthermore, the system can be configured to show how various activities affect BG levels so that young patients can understand the patterns themselves. For example, a slow animation can be generated by the system based on acquired input (eg, behavior, sensors, and status). In order to provide a sense of security to the parent, the system may include additional configurations that transmit information via progress reports about the child. Therefore, the parent can obtain a sense of security by giving the child more independence. Independence can be a two-way relationship, because if the parent continues to manage the child's health, the child's patient cannot achieve full self-management. In some areas, such high pressure parents can be referred to as “over parents”.

  Similar goals can be established for elderly patients being cared for by a family or nurse. Using the training example, the goal may provide a means for the health care team to manage the patient's progress and provide feedback to other loved ones / family members of the elderly.

The following list identifies additional goals that may be provided:
1. How long have you maintained no hits?
2. How many consecutive days did it not drop?
3. How many post-meal sessions did you do not exceed the threshold mg / dL?
4). How long have you maintained a rate of change below the threshold mg / dL / min?
5. Was a severe hypoglycemic event for a period (eg last month) less than a threshold number of times?
6). Was the hypoglycemia event for a certain period (eg 1 week) less than the threshold number of times?
7). Was the hyperglycemia event for a certain period (eg 1 week) less than the threshold number of times?
8). Was the glucose standard deviation below a threshold for a period of time (eg, the past week)?
9. Time within the target increased by a threshold amount (eg, percent).
10. Time of hypoglycemia event reduced by a threshold amount (eg, percentage).
11. Time of hyperglycemia event decreased by a threshold amount (eg, percentage).

  At block 502, a predetermined goal is provided. The predetermined target may be introduced at the time of manufacture. The predetermined goal may be based on the intended use of the device, such as glucose management. The predetermined goal may be introduced when initializing the patient to the device based on some basic input information received (eg, age, condition, language). An initial goal may be established based on an incoming response that selects a goal from a list of predetermined goals.

  In some implementations, the nurse may transmit information through an interface that identifies patient goals. For example, the goal may only be to address eating behavior for the next three months. Goals may be provided via an interface by members of a patient customer service (PCS) team working with the patient. For example, the goal may be caused by a patient request such as “the sensor insertion position does not seem comfortable”. As a means to assist this patient, the PCS member may transmit a goal that addresses where and how the sensor is inserted (eg, the sensor should be moved to the right).

  As described above, a goal is associated with a single user / patient. In some implementations, patients may be logically categorized into communities such as online communities, user communities, social media networks, patient care communities, and the like. By associating a goal with a community, the user can compete within the community and with other communities to achieve the goal. Such social interactions can increase device usage and enhance overall health outcomes.

  To identify the goal, the device can be configured to operate in a training mode. The training mode can be specified as a period of time (eg, two weeks after first being turned on). During the training mode, the device may be configured to collect input and identify and select a goal from a list of programmed goals. In some implementations, the device does not collect input, but may utilize a batch record import that includes patient behavior and status information. The imported information can then be used to identify one or more predetermined goals.

  In some implementations, the system may include a default goal. For example, glucose fluctuation rate, time it takes for a patient to transition from a first glucose level to a second glucose level (“conversion time”), “no hit” days, A1c reduction, interaction with data, sensor wear Default goals applicable to a wide range of possible outcomes such as continuity, time calibration, insulin delivery requirements, etc. may be defined.

  As described, device information may be received via an interface. The interface may include, but is not limited to, a visual interface such as a graphical user interface that includes one or more fields configured to obtain input to the system. In some implementations, the interface can be a voice interactive interface.

  The device may provide a search function. The device may receive query parameters for searching the device or other entities that are in data communication with the device (eg, content library, map server, Internet search engine, etc.). Since the search operation can be included as a behavior input, the adaptation can be based on the submitted query. For example, new goals can be identified based on natural language queries provided to the system. For example, if a search is detected that includes a query that says “How can I avoid an afternoon drop?”, The corresponding goal is set to help the user achieve the goal of avoiding an afternoon drop. Can be done. The goal may be identified as described above by comparing the received input information with one or more keywords associated with the goal.

  At block 506, ongoing behavior and / or status from other patients / metadata is obtained. As described above, information about a patient and other patients having a state similar to that patient can be stored remotely (eg, in the cloud). Users identified as facing a problem can provide suggestions for solutions that have worked. When the system receives a query (eg, how to prevent rebound degradation), the system retrieves previous rebound cases along with all available input (eg, what the user ate, What was the level of hormones, etc.), avoiding the same situation and comparing it with large data in the cloud of other users presenting actionable recommendations. The comparison can obtain aggregate data and perform matching on the device. In some implementations, the comparison can be done in server-client mode. In this mode of operation, the query can be augmented with some additional patient specific information and transmitted to the analysis engine in data communication with the device. Once processed, a response may be received by the device. Querying past users and extensive population data can provide a more powerful response.

  At block 504, user status and / or behavior information is collected from the user. FIG. 4 provides further details on how behavior and / or situation inputs are captured, tracked, determined, and shown, all of which are subroutines at block 504 of the adaptive goal setting process 500. Can be applied as That is, status and / or behavior inputs may be captured as described in block 402, and behavior and / or status inputs may be tracked over time to collect a database of information as described in block 404. The input may be processed to determine behavior and / or situation information about the patient as described in block 406, based on which the indication of the situation and / or behavior information is an optional block. Optionally, as shown at 408, and / or status and / or behavior information is entered directly into block 504 as described herein. The collection of information may include a doctor's prescription, a PCS team goal generated based on a call with the patient, or a goal that assesses the need that the user will achieve. Such information may be collected actively (eg, through a response received from a user through the device interface) or passively (eg, via a sensor).

  At block 508, one or more goals may be adapted based on information obtained about the patient (block 504) and other similar conditions (block 506). Adaptation may include changing the target criteria. Adaptation may include identifying additional goals for inclusion for the patient. Adaptation may include removing the patient's goal. Adaptation may include consideration of who initially defines the goal (eg, default, physician, PCS team member, himself, or team). For example, if the goal was a goal identified by a physician, the goal may not be automatically adaptable. For such goals, suggestions for adaptation are provided by the physician and can be applied after confirmation. Generally speaking, the patient should choose a goal, and the system should suggest a goal. In some implementations, the system may be configured to receive patient confirmation regarding addition of a proposed goal and / or adaptation to an existing goal.

  The system may be configured to adapt a predetermined goal based on criteria in some implementations. For example, if the user achieves the first goal, the goal may be adapted so that the goal is a little stricter. Alternatively, if the user does not achieve the goal, the system can adapt the goal to reduce the stringency of the criteria for the goal so that success can be achieved and / or understood. The reward for achieving the goal may include a badge. The badge may represent a virtual identifier associated with the user / patient. Badges can be awarded or a person's profile can be promoted to show a new status based on goal achievement.

  The system may be configured to automatically identify a new predetermined goal based on inputs and criteria from other factors such as food, exercise, insulin uptake, etc. as information becomes available to the system.

  In some implementations, the system may include a pattern recognition module. The pattern recognition module may be configured to look for differences between the received user input and the pattern associated with the typical user. For example, the system can take into account previous data sets from patients (eg, several weeks of data) and establish a pattern of glucose behavior as a basis or goal against which future data is compared. . If the glucose reading is identified where it is not the basis or goal determined from the glucose behavior pattern, a warning may be sent indicating that some abnormality has occurred. This may be associated with type 2 diabetic patients who are not taking drugs or are taking oral medications. Behavior pattern modification and identification is substantially different from normal patients. This pattern deviation may be a desirable feature for patients who have difficulty complying with a health care plan.

  As an example, consider a person wearing CGM. The nurse checked the CGM graph on the morning of the fourth day. The glucose reading was higher and more variable than normal. After some discussion, he noticed that he forgot to take the drug that morning. Even if the patient is looking at the data, the patient may not think about the missed dose until the nurse asks about it. The CGM can be adapted to identify pattern changes via pattern recognition and alert the patient.

  The described adaptive approach technique can also be used to set an adaptive target glucose level for a patient (eg, a diabetic patient not using insulin). The target level that will be displayed and possibly alerted may be based on previous history and goals that the patient was trying to achieve. Rather than setting a static level of warning, it can change dynamically to reflect improvements and changes to the target health level.

  The system may be configured to identify problematic areas or knowledge gaps based on behavioral or situational information received about the goal. Based on the tracking records, the system can be configured to adapt by creating goals that help users improve / learn in these areas. The goals created can be prioritized (eg, goals that are more important to the patient's health status) or can be random.

  At block 510, in some implementations, an adapted goal may be presented. For example, the adapted goal may be used in the context of the adaptive reporting process 200 shown in FIG. 2, such as block 206, whereby the adapted goal is compared with behavior and / or situation information. The presentation of the adapted goal may include a parallel comparison of the existing goal and the proposed adaptation. A message may be received by the system to affirm or deny adaptation. In this way, the user can exercise control over the changes specified by the system. The affirmation may be received via a visual interface such as a web form or social media network. Presentation and / or affirmation can occur out of band. For example, an e-mail or text message can be generated that includes the goal and the proposed adaptation. The email may include a unique identifier that may be included in a response email message from a user that allows changes. In such an implementation, the email server may be configured to receive the message and automatically transmit a message that acknowledges or rejects the adaptation to the monitoring device.

  The monitoring device may include a health optimization configuration that regulates the operation of the monitoring device. This configuration value is how much the user wants the system to adapt (eg, optimize) the user's goals and / or how much the user wants to interact with the device with respect to setting or confirming the user's goals. Can be provided as an indicator of the adaptation process.

  The goal presentation in block 510 may include a suggestion by an avatar, selection from a menu in some implementations. The presentation at block 510 may be triggered by adaptation. For example, the presentation at block 510 may occur when an adaptation is identified and / or applied. In some implementations, the presentation at block 510 may indicate the time (eg, the time when the most issues were seen based on the received input), the location (eg, the most issues based on the received inputs). ), The weather (eg, the temperature that caused the most problems), etc.

  The goal may be presented to the user of the monitoring device, but the goal may additionally or alternatively be an electronic medical record (EMR), parent / nurse, or closed loop control system (eg, settings, variables, inputs, alarms) • In some implementations, the presentation may also include providing goals to members of the group of which the user is a member. In this way, new goals useful for one user can be contributed to the community for use by other users.

  FIG. 6 is a process flow diagram of a method for providing patient training, improvement in diabetes management, and / or short term recommendations. Collectively, the provided content can be referred to as patient training. Patient training may be selected based on goals / criteria associated with the patient.

  The adaptive teaching process 600 shown in FIG. 6 may be implemented in whole or in part using a continuous monitoring system such as the device shown and described in FIG. The adaptive teaching process 600 may be implemented as a server process that is in data communication with a continuous monitoring device. The adaptive teaching process 600 is implemented via a field programmable gate array or application specific integrated circuit or microcontroller, etc. that is specifically configured to implement one or more aspects of the adaptive teaching process 600 described. Can be implemented in hardware.

  A process that provides adaptive guidance based on behavioral and / or situational information to create a general purpose device for health care applications or a health care device intended for use in a wide range of user preferences in a simple and intuitive manner The long-standing need for personalization is solved. That is, not all users have the same preferences when it comes to personalizing physiological information guidance or training for medical devices, particularly customer-driven medical devices. Some users are particularly motivated and can quickly understand a number of basic concepts associated with the use of medical devices, while others may require more guidance or training. Many users are in the middle, and their preferences can be influenced by contextual situations. Unfortunately, the creation of highly customizable devices is highly complex and vice versa and does not support full user coverage. There remains a need for an automatic and adaptable understanding of the behavior and status of customer-driven devices that are highly intelligent and allow for teaching or training adaptation. In one implementation, these needs may identify the need for guidance to the patient based on behavior and / or situation information (602), provide guidance to the user (604), and additional queries, behaviors Receiving the situation, or physiological information (606), and the device is extremely difficult for a human to perform as otherwise enabled by the systems and methods described herein, Efficient, intuitive, and intelligent health management without the need to understand complex or comprehensive technologies, human behavior (or situations), and health data that may seem inefficient and impossible And can be personalized for use optimization.

  “Adaptive instruction” or “adaptive training” generally refers to a process, property, or action that provides instruction based on received information associated with a user's behavior or situation. In some implementations, adaptive instruction is based on predictive reasoning derived from information gathered about relevant users. An adaptive teaching system or method may be contrasted with a reactive teaching system or method. A reactive instruction system or method may provide a single reactive instruction in real time (eg, in response to a stimulus) based on a single event or selection, while an adaptive instruction system or method is Predict events based on previous user behaviors or situations specified in, and make progressive adjustments to teaching or training based on them.

  The adaptive guidance process 600 identifies and provides adaptive guidance to patients related to the use of continuous monitoring systems and / or management of diabetic conditions associated with monitoring. Guidance may be based on training needs identified based on received patient-related inputs (behavioral and / or situational information). The need for adaptive instruction can be identified based on queries submitted by the patient via a search function included in the monitoring device. For example, a natural language query can be received by the monitoring device. A keyword can be specified by character processing of a query. Query keywords (and historical keywords in some implementations) can be used to identify concepts that patients are asking a lot of questions. The amount of questions can indicate that more training is needed on the subject. In some implementations, natural language queries may include: “Predict nighttime glucose levels and insulin requirements”, “How do I adjust basal insulin settings?”, “Amount / type / time of bolus insulin Can be received via the provided pre-selected query formats such as “How?”, “What is the amount / type / time of exercise?”, “What is the amount / time / location / content?”

  At block 602, the need for guidance is identified based on behavior and / or situation information obtained for the user. The acquisition can be performed as described with reference to FIG. 4 and can be provided herein as a subroutine. That is, status and / or behavior inputs may be captured as described in block 402, and behavior and / or status inputs may be tracked over time to collect a database of information as described in block 404. The input may be processed to determine behavior and / or situation information about the patient as described in block 406, based on which the indication of the situation and / or behavior information is an optional block. Optionally, as shown at 408, and / or status and / or behavior information is entered directly into block 602 as described herein. As described above, behavior and / or status information may be received from an external device, collected by a sensor, or determined based on input information. The information can include a query received via the monitoring device. As discussed, in some implementations, a weight associated with each information element may be obtained. For example, the status information may be weighted by the patient's personal preference, such as “I prefer organic food over processed food”, “Vegetarian”, or “I like running rather than cycling”. Based on these preferences, whether expressed directly or specified based on behavior and / or situation, adapt and assign how much weight influences the situation input and the specific input The criteria for initiating the criteria evaluation process during the search can be pre-defined in the system, where certain specific behavior and / or situation information is used to identify the need for patient training. Define criteria.

Other questions that may identify additional training opportunities include the following:
1. When / what to eat or drink [here is a description of exercise]?
2. What should we do today to achieve our weight loss goals?
3. Suggested restaurant or food, quantity and exercise 4. Can I replace exercise with insulin? How much?
5. What happens to glucose within minutes?
6). Can the route be completed without food intake based on input information received from the navigation system?
7). When should it be eaten? How much?
8). Suggest a restaurant on the way.
9. What is the estimated morning glucose?
10. What should be done to make the estimate x?
11. How should we handle this decline / rise?
12 What should I buy (or stop buying) at a grocery store?
13. Automatic grocery store list

  Additionally or alternatively, training / teaching needs may be identified at 602 based on the comparison of behavior or situation information at block 206 with goals or criteria. For example, if the goal for the patient is to increase interaction with the device (and optionally adaptation to the reporting style does not lead to progress towards achieving that goal), the training process may be initiated, It identifies the need for training (increased interaction with the device) and provides training (adaptive guidance) on how to best interact with the device (604).

  Additionally or alternatively, the need for training / teaching may be identified at 602 based on the adaptive goal setting process 500, which is a determination of behavior or situation information (within the behavior and / or situation information determination process 400). based on. For example, behavior / situation based goal adaptation (at 508) identifies the need for training / teaching (602) and adaptively provides guidance (604) towards the adapted goal. In some cases, if the adapted goal is more strict than the previous goal, adaptively provide guidance on how to achieve the adapted goal (604) (602). In some cases, if the adapted goal is less stringent than the previous goal (eg, resulting from a continuous failure to achieve the previous goal), the user's The need for training / teaching to provide the user with adaptive guidance to improve behavior (604) may be identified (602). In some cases, if the adapted goal is a new type of goal for the patient, the need for training / guiding to provide adaptive guidance to the patient towards achieving the goal is identified (604) (602).

  As part of collecting behavior and / or situation information, natural language queries may be processed along with physiological information and / or behavior / situation information. By combining the processing of physiological information and behavior / situation information, the processing of queries (eg, natural language queries or structured language queries) can be answered more personally and contextually.

  A natural language query may take the form of a question from a user received by the system. For example, “I'm hungry, what should I eat?” Natural language queries, however, do not necessarily have to be in the form of questions. By providing a statement, a query may be triggered based on the natural language processing the received statement. For example, the statement “I am exercising now” may cause the system to determine that it tends to hit a drop in glucose 30 minutes after the user starts exercising. For such users, the system will help the user to avoid the decline: “You may want to ingest x carbohydrates and alert reminders to check glucose levels within 3 hours. Can provide a suggested message.

  In some implementations, query processing may include artificial intelligence processing. One artificial intelligence technique that can be applied is “backpropagation”. In the backpropagation process, criteria and inputs for changes that affect the system are weighted. The system may determine how frequently input occurs, decreases with increasing input of different weights, increases / decreases over time, one or more factors (eg, user preference, time of day, weather) Dynamically adjust weights based on things like proportionality.

  In the context of natural language queries, the system is configured to adapt weighted criteria in some implementations. Weighting may be based on the number of times the question has been repeated, the number of times food has been purchased based on system recommendations, and / or the removal of meat recommendations after several requests for a vegetarian diet / restaurant .

  At block 604, adaptive guidance (and / or adaptive training) is provided regarding the needs identified based on patient behavior and / or situation information. In some implementations, for example, based on identified needs, patient physiological information, along with behavioral and / or situational information, is considered in the process of adaptive teaching. By considering both physiological information as well as behavior / situation information from a continuous monitoring system, training and / or instruction can be made more personal without having to answer multiple questions and bother the user. In implementations that feature structured language queries, only the first question is structured, and the remaining information can be provided once a portion of the query is determined or collected as described above.

  The adaptive instruction generated at block 604 suggests, for example, a salad from one of the following local restaurants x, y, or z, drinking X ounces of Y per hour, etc. An answer to the query may be included. The recommendations may be based on a database query of information coupled with the monitoring device. In some implementations, the query can be transmitted to the server for processing and the response received by the monitoring device.

  Guidance can be provided not only to the user initiating the query, but also to parents, children (for older people), loved ones, doctors, diabetes care leaders (CDE), health insurance companies, social media support groups, etc. . By providing this information to family members, loved ones, or health care teams for users of all ages (adults or children), it can help provide more secure use and reduce "diabetes police" However, if the parent feels comfortable with the child's training / diabetes knowledge development, it can help the child gain further independence from the parent.

Guidance may include activating features of the monitoring device, such as calling a doctor or spouse / parent / friend. Features of the system can be activated in response to an input request. The system may select an input request based on behavior and / or situation information about the user. Examples of input requests include the following:
“Do you want to exercise now? X You may want to eat carbohydrates and set a warning reminder to check your glucose levels within 3 hours.”
“Did you eat now? How many carbohydrates did you have in your diet? Was it a simple carbohydrate diet or a complex diet with lipid / protein? Intake of insulin or x-units of insulin Please consider. "
“Is it driving? I recommend taking a short break and taking a snack.”

  In some implementations, training instructions and / or responses may be provided through an avatar, which guides the user through training, advice, assistance, and / or otherwise answers patient questions and / or Provide useful information to help provide training to address identified training needs.

  At block 606, additional natural language, behavior and / or context feedback may optionally be received. The feedback can include comments on the response. The comment can be transmitted via the monitoring device. The system may prompt the user to comment to obtain as personalized information as possible from the user without requiring clear user interaction (ie, without necessarily asking direct questions). As shown in FIG. 6, the adaptive teaching process 600 may return to block 604 for further processing.

  Feedback information can help scrutinize queries. For example, expected duration of exercise, level of effort, what was eaten at breakfast, carbohydrate intake, or relative status (eg, disease, stress, excitement in steps 1-10) is obtained. obtain. The system can be configured to obtain additional information and reprocess the search for additional information. In some implementations, input requests for additional information may be based on the number of results of the initial query. For example, if too many hits are found for a patient query “how to lose weight”, feedback on favorable exercise or food can be obtained to help narrow the results.

  The described methods and systems may be applicable to diabetes management. In the context of diabetes management, personalized assistance in maintaining analyte levels within the target range or reaching the desired target range is provided by the features described. How do I adjust my basal insulin settings, what is the amount / type / time of bolus insulin, what is the amount / type / time of exercise, and / or what is the amount / time / location / content of meals? A pre-specified query to be included can be included in the system. This system includes caloric intake derived from photo analysis software, physical measurements that can be measured or specific to glucose trend graphs, exercise information from fitbits, glucose sensor information from BG meters or CGM, insulin delivery devices Input information from various sources may be processed, such as the amount of insulin delivered from, the on-board calculated values, and / or information provided or calculated by other devices. The system and method may also obtain information from a personal calendar or social media site with which the person is associated. Adaptation is based on machine learning of patterns such as weights. The system and method further includes feedback that allows a request for additional information (eg, where are they?). The described aspects further provide an output that includes an answer to the question (eg, suggesting a salad from one of the following local restaurants x, y, or z).

  People who review past glucose data have been shown to have better diabetes management. One non-limiting advantage of the described system and method includes capturing a time stamp regarding how often historical glucose data is checked. If the user has not verified the past data for a given period, the system can adapt the type, frequency, and type of reminders to the user. The reminder may include information that reviewing past data is an important part of diabetes management. This can be combined with other pattern recognition to generate information about the user's past data.

  Diabetes management can be performed by a person through behavior and actions. Adaptation and feedback can be used to help people manage the condition. Diabetes management can also be implemented using a control system, such as a closed loop control system. By providing behavior and status information to one or more users of the system, the system can be adapted over time to provide more effective, accurate, and coordinated management of an individual's condition.

  The described features can be applied in non-diabetic patients and type 2 weight loss situations. A simple target caloric intake can be determined based on calorie consumption. The goal may include reducing a certain number of pounds over a period of time. If the goal is to reduce 10 pounds in 3 weeks, it may be necessary to eat a meal that is 500 calories less than the number consumed per day. Calorie consumption is recorded daily and the next day's caloric intake is adaptively generated.

  Thereby, the glucose target of type 2 insulin-free diabetic patients can be estimated. The system or method may be configured to analyze glucose, calories, and exercise behavior and / or situation information. Based on the comparison of the received information with the target, a target for the next day may be generated. For example, the system may generate and provide recommendations to exercise 10 minutes more today to reduce sugar intake by 5% to achieve a glucose target. Recommendations can be calculated based on patient specific input information, including weighting of specific factors to be considered.

  An implementation of athletic performance optimization may incorporate one or more of the features described above. For example, the surveillance device may say, “When to eat 6 miles to run (or what to eat / insulin to do within 1 hour before exercising, May be started) ”or a natural language query such as“? ”May be received. In the capacity optimization situation, behavior and / or situation inputs include hydration level, heart rate, target heart rate, internal temperature, external temperature, external humidity, internal analyte, hydration input, or force output ( One or more of cycling) may be included. The system may be configured to process the query using natural language processing, data mining, and / or machine learning with the provided input / behavior information to process the query. In some implementations, the query may be scrutinized based on additional feedback, such as expected exercise duration, level of effort, what you ate for breakfast, etc., carbohydrate intake. Based on the received input information, the system may be configured to generate a suggested athletic performance plan, such as drinking X ounces of Y within an hour.

  A further example of a region that can include the described features is a weight loss monitor. In this example, the monitor is a query (natural or structured) such as "Do I have to do today to achieve my weight loss goal?" Or "Would you recommend a restaurant or food, quantity and exercise?" Can receive. The monitor may also receive physiological inputs such as glucose levels, lactate, free fatty acids, exercise heart rate, and / or IgG-antigliadin, along with the physiological inputs, the system may behave and / or status information ( For example, current weight, BMI, daily target calorie (consumption), daily target calorie (burning), location, favorite food, effort level, etc. may be processed. The process provides a suggested schedule of activities and food based on the received input.

  FIG. 7 is a functional block diagram of a continuous monitoring device including an adaptive interface. Device 700 includes an input receiver 702. Input receiver 702 is configured to obtain behavioral, status, or physiological input values. Values may be received from sensors, information systems, social media, voice responses, actions on device 700 (eg, search), and others described above. The input receiver 702 may be wired (for example, Ethernet (registered trademark), USB, HDMI (registered trademark), coaxial cable, telephone, patch cable, optical fiber cable) or wireless (for example, WiFi, Bluetooth) for acquiring input information. (Registered trademark)) communication means.

  As shown in FIG. 7, the input receiver 702 is connected to the input processor 704. Input processor 704 may be configured to process received input. Input processor 704 may be configured to process received input based on processing rules obtained from processing rules database 706. Input processor 704 may receive input data along with a source of data. Based on this source, processing rules may be selected from the processing rule database 706. Processing rules may indicate the format of the input data, an appropriate parser, or other information to facilitate the extraction and categorization of information contained in the input data.

  Input processor 704 may provide the extracted information to weighting processor 708. The weighting processor 708 is configured to determine the weight of each value extracted from the input data. As mentioned above, some inputs can affect the adaptation process more strongly than others. The weighting processor 708 is configured to identify these weights. The weighting processor 708 may be in data communication with the past input value database 710. The past input value database 710 includes past input values of the user. In some implementations, the weighting processor 708 is configured to generate weights based on accumulated input information of multiple users (eg, big data analysis of similarly suitable user communities). The request can be transmitted to a remote server.

  The weighted input value may be provided to the adaptation engine 712. The adaptation engine 712 is configured to identify and apply one or more of the adaptations described above, such as device adaptation, target adaptation, interface adaptation, training or content adaptation. The adaptation engine 712 may identify one or more adaptations that are included in the adaptation rules database 714. The adaptation rule database 714 may include one or more adaptations to apply based on input values. For example, if the input value indicates low glucose, a set of adaptations indicating possible adaptations for increasing glucose levels may be stored in the adaptation rules database 714.

  The adaptation engine 712 shown in FIG. 7 is in data communication with the content database 714. The content database 714 may include categorized content that can be searched based on input values. Thus, the multimedia movie can be stored with a glucose threshold level (eg, low). Based on the input glucose reading, a movie can be retrieved from the content database 714 for presentation.

  The adaptation engine 712 shown is also in data communication with the target database 716. The goal database 716 may be configured to store goals and associated criteria. The goal database 716 may be configured to store template goals along with predetermined criteria. The goal database 716 may be configured to store goals for a particular user or user group. The adaptation engine 712 may identify adaptation rules that indicate setting or adjusting an existing goal.

  As shown in FIG. 7, device 700 includes a transmitter 718. Transmitter 718 may receive the identified adaptation and transmit the change. The transmitter 718 can be wired (eg, Ethernet®, USB, HDMI®, coaxial cable, telephone, patch cable, fiber optic cable) or wireless (eg, WiFi, Bluetooth (registered trademark) communication means.

  In some implementations, the transmitter 718 may be configured to communicate the proposed adaptation before applying the adaptation. In some implementations, the transmitter 718 may be configured to transmit an adapted message (eg, alert, text message, email, FTP, HTTP, or others).

  As shown in FIG. 7, the device 700 also includes a target tracker 720. The target tracking device 720 is configured to determine the state of the target based on the received input. For example, upon receiving glucose data, the goal tracking device 720 may retrieve all valid goals for the user associated with the glucose data. The goal tracker 720 may then determine whether the received input value meets the glucose level criteria included in the identified goal. The result of the determination may be provided to transmitter 718 for transmission. In some implementations, the transmission may include a reward transmission as described above.

  The connection between the elements shown in FIG. 7 illustrates an exemplary communication path of device 700. Additional communication paths, either directly or through intermediate means, may be included to further facilitate device 700 information exchange. The communication path can be a two-way communication path that allows the indicated elements to exchange information.

  As used herein, the term “determining” encompasses a wide range of actions. For example, “determining” includes computing, computing, processing, deriving, exploring, searching (eg, searching a table, database, or another data structure). Confirmation, etc. may be included. Further, “determining” can include receiving (eg, receiving information) and accessing (eg, accessing data in a memory). Also, “determining” can include resolving, selecting, selecting, establishing and the like.

  As used herein, the term “message” encompasses a wide variety of formats for transmitting information. A message can include a machine-readable collection of information, such as an XML document, a fixed field message, a comma delimited message, and the like. A message may include a signal used in some implementations to transmit one or more indications of information. Although described in the singular, it will be understood that a message may be composed / transmitted / stored / retrieved in multiple parts.

  The various operations of the methods described above are performed by any suitable means capable of performing the operations, such as various hardware and / or software component (s), circuits, and / or module (s). obtain. In general, any operation illustrated in the drawings may be performed by corresponding functional means capable of performing the operation.

  Various exemplary logic blocks, modules, and circuits (eg, the blocks of FIGS. 2 and 7) described in connection with this disclosure may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits ( ASIC), field programmable gate array signal (FPGA), or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components, or designed to perform the functions described herein It can be implemented or implemented in any combination thereof. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any commercially available processor, controller, microcontroller or state machine. The processor may also be implemented as a combination of computing devices, eg, a DSP and microprocessor combination, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

  In one or more aspects, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. By way of example and not limitation, such computer readable media can be RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic storage or other magnetic storage device, or instructions or data. Any other medium that can be used to hold or store the desired program code in the form of a structure and that can be accessed by a computer can be included. In addition, any connection is a properly named computer-readable medium. For example, software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technology such as infrared, wireless communication, and microwave. In this case, coaxial technology, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, wireless communication, and microwave are included in the definition of media. As used herein, a disc and a disc are a compact disc (CD), a laser disc (registered trademark), an optical disc, a digital versatile disc (DVD), a floppy (registered trademark) disc, And a Blu-ray disc, the disc normally reproduces data magnetically, while the disc reproduces data optically using a laser. Accordingly, in some aspects computer readable media may include non-transitory computer readable media (eg, tangible media). In addition, in some aspects computer readable media may include transitory computer readable media (eg, signals). Combinations of the above should also be included within the scope of computer-readable media.

  The methods disclosed herein include one or more steps or actions for achieving the described method. The method steps and / or actions may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or actions is indicated, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the claims.

  Thus, certain aspects may include a computer program product for performing the operations presented herein. For example, such a computer program product comprises a computer-readable medium having stored thereon (and / or code) instructions executable by one or more processors to perform the operations described herein. obtain. For certain aspects, the computer program product may include packaging material.

  Software or instructions may also be transmitted over a transmission medium. For example, software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technology such as infrared, wireless communication, and microwave. In this case, coaxial technologies, fiber optic cables, twisted pair, DSL, or wireless technologies such as infrared, wireless communication, and microwave are included in the definition of transmission media.

  Moreover, modules and / or other suitable means for performing the methods and techniques described herein can be downloaded and / or otherwise obtained by user terminals and / or base stations as appropriate. Please understand that. For example, such a device can be connected to a server to facilitate the transition of means for performing the methods described herein. Alternatively, the various methods described herein can be stored in a storage means (e.g., a user terminal and / or base station so that the various methods can be obtained after connecting or providing the storage means to a device). RAM, ROM, a physical storage device such as a compact disk (CD) or a floppy disk, etc.). In addition, any other suitable technique for providing the methods and techniques described herein may be used.

  It is to be understood that the claims are not limited to the precise configuration and components illustrated above. Various modifications, changes and variations may be made in the arrangement, operation and details of the methods and apparatus described above without departing from the scope of the claims.

  Unless otherwise defined, all terms (including technical and scientific terms) are given their ordinary and customary meaning to those of ordinary skill in the art and are limited to special or customized meanings unless explicitly defined herein. Is not to be done. The use of a particular term in describing a particular feature or aspect of the present disclosure is intended to be any definition of the feature or aspect of the present disclosure to which that term relates, as that term is redefined herein. It should be noted that it is not considered to be implied to include general characteristics. The terms and phrases used in this application, and variations thereof, in particular the appended claims, should be considered unconstrained as opposed to limiting unless explicitly stated otherwise. As an example of the foregoing, the term “including” means “including without limitation”, “including but not limited”, etc., and includes “comprising”. The term “as used herein is synonymous with“ including ”,“ containing ”, or“ characterized by ”and is inclusive or constrained And does not exclude additional undescribed elements or method steps, the term “comprising” should be interpreted as “having at least”, and the term “including” , “Including but not limited to”, and the term “example” provides an illustrative example of the item being discussed Are not intended to be exhaustive or restrictive, and adjectives such as “known”, “ordinary”, “standard” and similar meaning terms are used to describe the item being described. Should not be considered limited to items available at a given time or given time, but known, normal, which may be available or known at any time now or in the future Or should be construed to encompass standard techniques, and terms such as “preferably”, “preferred”, “desired” or “desirable” and words of similar meaning may have certain characteristics, It should not be understood to imply that it is critical, essential, or even important for the structure or function of the present invention, but may merely be utilized in a particular embodiment of the present invention. Or not It is intended to emphasize the good alternative or additional features. Similarly, a group of items associated with the conjunction “and” should not be construed as requiring that any and all of the items be present in the group, and unless explicitly stated otherwise, “and / Or ". Similarly, groups of items associated with the conjunction “or” should not be construed as requiring mutual exclusion between the groups, but as “and / or” unless expressly stated otherwise. It should be.

  Where a range of values is provided, upper and lower limits, as well as each intermediate value between the upper and lower limits of the range, are included in the embodiment.

  With respect to the use of substantially all plural and / or singular terms herein, those skilled in the art will recognize from the singular and / or singular as appropriate to the situation and / or application. Can be converted to plural form. Various singular / plural permutations may be expressly set forth herein for sake of clarity. The indefinite article “a” or “an” does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measurements are recited in mutually different dependent claims does not indicate that a combination of these measurements cannot be used to benefit. Any reference signs in the claims shall not be construed as limiting the scope.

  Where a specific number of introduced claims are intended to be described, such intention is expressly stated in the claims, and if not stated, such intention is It will be further understood by those skilled in the art that it does not exist. For example, as an aid to understanding, the claims appended hereto may include the use of the “at least one” and “one or more” prefixes to introduce the claim description. However, the use of such terms is subject to the same claims as “one or more” or “at least one” prefix and “one (a)” or “one”. Indefinite articles such as “one (a)” and / or “one” should typically be interpreted to mean “at least one” or “one or more”. In the case of an indefinite article such as “one (a)” or “one (an)”, an introductory statement of a claim is intended to describe the description of such introduced claim. It is not to be construed as implying that any particular claim it contains will be limited to embodiments containing only one such description, which is used to introduce the following description of the claims. This applies to the use of definite articles. In addition, even if a specific number of written claims are explicitly stated, such a description should typically be interpreted to mean at least the stated number. Will be understood (eg, the verbal description of “two descriptions” typically means at least two references or more than one reference without a modifier), and “A, In the case where a conventional analog to “at least one of B, C, etc.” is used, generally such a restriction is a single member, including any combination of the listed items, for example. (Eg, “a system having at least one of A, B, and C” includes A alone, B alone, C alone, A and B together, A and C together, and B and C together). Together and / or A, B, and As will both contain a system such as a C, but not limited to) those of skill in the art are intended in the sense that understanding the convention. In cases where a conventional analog to “at least one of A, B, C, etc.” is used, such a limitation is generally intended in the sense that one of ordinary skill in the art understands the convention ( For example, “a system having at least one of A, B, or C” includes A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or Or systems such as having A, B, and C together, but not limited to these). Whether virtually all disjunctions and / or phrases that represent two or more alternative terms are in the description, claims, or drawings, one of those terms, It will be further understood by those skilled in the art that it is understood that the possibility of including either or both terms is included. For example, it will be understood that the phrase “A or B” includes the possibilities of “A” or “B” or “A and B”.

  All numbers representing amounts of ingredients, reaction conditions, etc. shall be understood as being modified in all cases by the term “about”. Thus, unless indicated to the contrary, the numerical parameters described herein are approximate values and may vary depending on the desired properties sought to be obtained. Finally, not as an attempt to limit the application of the doctrine to any claims in any specification claiming priority over this specification, each numeric parameter shall have significant digits and conventional rounding. Should be interpreted in view of the approach.

  All references cited herein are hereby incorporated by reference in their entirety. To the extent that publications and patents or patent applications incorporated by reference contradict the disclosure contained herein, this specification may supersede and / or precede any such conflicting material. Intended.

  Headings are included herein to help locate references and various sections. These headings are not intended to limit the scope of the concepts described therewith. Such a concept may have applicability throughout this specification.

  Moreover, while the foregoing has been described in some detail by way of illustration and example for purposes of clarity and understanding, it will be apparent to those skilled in the art that certain changes and modifications may be practiced. Accordingly, the description and examples should not be construed as limiting the invention to the specific embodiments and examples described herein, but all modifications and alternatives with the true scope and spirit of the invention. It covers all means.

2 Drug delivery pump 4 Reference meter 8 Sensor system 10 Continuous analyte sensor 12 Sensor electronics module 14 Small display device 16 Portable receiver 18 Display device 20 Computer workstation 21 Wearable device 22 Processor 24 Network 100 Analyte monitoring system 700 Device 702 Input Receiver 704 Input Processor 706 Processing Rule Database 708 Weighting Processor 710 Past Input Value Database 712 Adaptation Engine 714 Content Database 716 Target Database 718 Transmitter 720 Target Tracking Device

Claims (86)

A method for adaptive configuration of an analyte monitoring device comprising:
Transmitting a first report regarding the physiological information of the host using a first report format that includes a first report format characteristic;
Determining at least one of behavior or situation information including at least one behavior or situation characteristic of the host;
Comparing the at least one behavior and / or situation characteristic to one or more behavior or situation criteria;
Adjusting the report format based at least in part on the comparison, wherein the report format includes a second report format characteristic that is different from the first report format characteristic;
Using the second report format to transmit a second report relating to physiological information;
Said method.   The method of claim 1, wherein the first report includes a trend graph of the physiological information over a period of time. Determining the behavior or situation information includes
Receiving a message from the sensor including data associated with the host;
Identifying a characteristic extractor based on the message and the sensor;
Generating the at least one behavior or situation characteristic based on the received message via the identified characteristic extractor;
Associating the generated characteristic with the behavior or status information;
The method according to claim 1 or 2, comprising: Determining the behavior or situation information includes
Capturing a value from a pre-specified input indicative of a behavior or situation associated with the physiological state of the host;
Periodically storing additional values received from the pre-specified inputs, creating a record of user-specific pre-specified input values;
Periodically determining behavior or status information about the host based on a record of the user-specific pre-specified input values captured over time;
The method according to claim 1, comprising:   5. The method of any of claims 1-4, further comprising transmitting the determined behavior or status information regarding the host.   The pre-specified input includes at least one of a blood glucose meter, a thermometer, an accelerometer, a camera, a microphone, a query processing engine, an electronic device configured for communication between machines, or an electronic patient record. The method according to claim 4 or 5.   7. The method of any of claims 4-6, wherein storing additional values periodically includes storing a time stamp indicating when a particular additional value was stored.   8. The method of any of claims 4-7, wherein the physiological condition comprises one or more of diabetes, obesity, malnutrition, hyperactivity, depression, fertility. Determining behavior or status information about the host includes
Selecting one of a plurality of pre-specified input values included in the record;
Identifying one or more behaviors or situations based on a comparison of the selected input value and the input that provides the selected value with an identification value associated with a plurality of behaviors or situations;
The method according to claim 4, comprising:   10. The method according to any of claims 4-9, wherein determining behavior or status information about the host comprises processing the pre-identified input values included in the record.   11. The method of any of claims 4-10, wherein processing the value includes identifying a trend for the value.   12. The method of any of claims 1-11, wherein comparing the characteristic to one or more behavior or situation criteria comprises comparing the characteristic to a behavior or situation criteria associated with a goal.   The goal is the interaction with the device, the amount of time within the target, the amount of time outside the target, the location of the device, the data retention time, the calibration frequency, the standard deviation, the pattern management, the time spent on a certain screen, 13. The method of claim 12, wherein the method is selected from the group consisting of time spent in a low state, time spent in a high state, time spent with a high rate of change, or time spent with a low rate of change.   14. The method of any of claims 1-13, wherein comparing the characteristic to one or more behavior or situation criteria comprises comparing the characteristic to behavior or situation criteria associated with interface adaptation. .   The interface adaptation includes warning frequency, warning volume, warning tone, display font, display font size, display font color, message delivery destination address, message delivery destination telephone number, list of menu items, or operation setting of the analyte monitoring device. 15. The method of claim 14, comprising at least one of them. Transmitting a message identifying the adjustment;
Activating the second reporting format for subsequent reporting upon receipt of the confirmation of the adjustment;
Activating the first reporting format for subsequent reporting if a rejection of the adjustment is received or if no response to the message is received;
The method according to claim 1, further comprising:   17. The method according to any of claims 1 to 16, wherein the first report is transmitted to a common destination with the second report.   18. The method according to any of claims 1 to 17, wherein the first report is transmitted to a first destination and the second report is transmitted to a second destination.   19. The method of any of claims 1-18, wherein the different first and second report format characteristics include at least one of alarm frequency, tone, or volume.   The different first and second report format characteristics are at least one of trend graph resolution, brightness intensity, graph color, interface graphic, interface symbology, or magnification level of information displayed. 20. The method according to any of claims 1-19, comprising:   21. The one of claims 1-20, wherein the different first and second reporting format characteristics comprise at least one of a trend graph orientation, a trend graph range, a graph color scheme, or a dynamic trend graph. The method according to claim 1.   The different first and second reporting format characteristics include at least one of reporting frequency, number of specific types of alerts, amount of avatar assistance, vibration intensity, vibration frequency, or amount of data to display. The method according to any one of claims 1 to 21.   The different first and second report format characteristics include: default display of the report, discretionary level for status-based reporting, input configuration for reporting, glucose acceleration information, prediction mode time, or future mode 23. The method according to any of claims 1-22, comprising at least one of time / input.   The different first and second report format characteristics include at least one of a screen order, menu item order, hidden item order, frequency of information transmitted, or content of information transmitted. 24. The method according to any of claims 1-23.   25. The method of any of claims 1-24, wherein the transmission is to at least one of a continuous monitoring device, a patient record system, a smartphone, or a social media internet site.   26. The transmission according to any of claims 1 to 25, wherein the transmission comprises transmitting via a human detectable interface in at least one of a continuous monitoring device, a patient record system, a smartphone, or a social media internet site. Said method. An integrated system for monitoring glucose concentration in a host and for delivering insulin to the host,
A continuous glucose sensor configured to measure glucose concentration at a host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 1-26;
The integrated system comprising: An electronic device for monitoring glucose concentration in a host,
A continuous glucose sensor configured to measure glucose concentration at a host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
A processor module configured to perform any of the methods of claims 1-26;
The electronic device comprising: An electronic device for delivering insulin to a host,
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 1-26;
The electronic device comprising: A system for adaptive configuration of an analyte monitoring device comprising:
An input receiver configured to receive at least one of status information, behavior information, or physiological information about the host over a period of time;
An input processor configured to identify a situation or behavior based at least in part on information received over time;
An adaptive engine configured to provide an adaptive report to an analyte monitoring device based on the identified situation or behavior using the method of any of claims 1-26;
Comprising the system. A method for identifying host adaptation information, comprising:
Capturing a value from a pre-specified input indicative of a behavior or situation associated with the physiological state of the host;
Periodically storing additional values received from the pre-specified inputs, creating a record of user-specific pre-specified input values;
Periodically determining behavior or status information about the host based on a record of the user-specific pre-specified input values captured over time;
Said method.   32. The method of claim 31, further comprising transmitting the determined behavior or status information regarding the host.   35. The method of claim 32, wherein transmitting comprises transmitting to at least one of a continuous monitoring device, a patient record system, a smartphone, or a social media internet site.   The pre-specified input includes at least one of a blood glucose meter, a thermometer, an accelerometer, a camera, a microphone, a query processing engine, an electronic device configured for communication between machines, or an electronic patient record. 34. The method according to any of claims 31-33.   35. The method of any of claims 31-34, wherein storing additional values periodically includes storing a timestamp indicating when a particular additional value was stored.   36. The method of any of claims 31-35, wherein the physiological condition comprises one or more of diabetes, obesity, malnutrition, hyperactivity, depression, fertility. Determining behavior or status information about the host includes
Selecting one of a plurality of pre-specified input values included in the record;
Identifying one or more behaviors or situations based on a comparison of the selected input value and the input that provides the selected value with an identification value associated with a plurality of behaviors or situations;
37. The method according to any of claims 31 to 36, comprising:   38. The method of any of claims 31 to 37, wherein determining behavior or status information about the host comprises processing the predefined input values included in the record.   39. The method of claim 38, wherein processing of the value includes identifying a trend for the value.   The pre-specified inputs are: amount of interaction, glucose warning / alarm status, sensor data, number of screen hits, alarm analysis, characteristics associated with host response, time to response, blood glucose management associated with the response , User feedback associated with the alarm, not recognizing warning / alarm within x minutes, time to recognize warning / alarm, time in warning state, CGM data, insulin pump data, insulin sensitivity, pattern, activity data Calorie data, free fatty acids, heart rate during exercise, IgG-antigliadin, stress level sweat / sweat level from skin patch sensor, free amino acids, troponin, ketone, ketone, adipanectin, troponin, sweating, Or at least one of body temperatures. The method according to any one.   41. The method of any of claims 31 to 40, wherein the pre-specified input comprises at least one of a person's biology, location, sensing status, or environmental data.   The pre-specified inputs are hydration, heart rate, target heart rate, internal temperature, external temperature, external humidity, internal analyte, hydration input, power output, sweat rate, pace, adrenaline level, stress, Of disease / disease, metabolism / calorie consumption rate, lipolysis rate, current weight, BMI, desired weight, target daily calories burned, target daily calories burned, location, favorite food, or level of effort 42. The method according to any of claims 31 to 41, comprising at least one.   43. The method of any of claims 31-42, wherein the pre-specified input comprises a detected improvement or a stored goal / reference success rate.   44. The periodic determination of behavior or status information relating to the host includes identifying a pattern of behavior or status information based on recognition of a predetermined pattern of the pre-identified input. The method according to any one of the above.   45. The method of any of claims 31-44, comprising providing an indication of the identified status and / or behavior information. Comparing the at least one behavior and / or situation characteristic to one or more behavior or situation criteria;
Adjusting a report format based at least in part on the comparison, wherein the report format includes a report format characteristic that is different from a previous report format characteristic;
46. The method of any one of claims 31 to 45, comprising: Generating one or more behavior or situation criteria for the target based on the determined behavior or situation information;
Generating a goal based on the generated criteria;
47. The method according to any of claims 31 to 46, comprising: Identifying a need for training or a need for required instruction based on the behavior / situation information about the host;
Providing training or guidance based on physiological information associated with the behavior / situation information about the host in response to the identified need;
48. The method of any of claims 31 to 47, comprising: An integrated system for monitoring glucose concentration in a host and for delivering insulin to the host,
A continuous glucose sensor configured to measure glucose concentration at a host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 31-47;
The integrated system comprising: An electronic device for monitoring glucose concentration in a host,
A continuous glucose sensor configured to measure the glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
A processor module configured to perform any of the methods of claims 31-47;
The electronic device comprising: An electronic device for delivering insulin to a host,
An insulin delivery device configured to deliver insulin to a host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 31-47;
The electronic device comprising: An adaptive goal setting method for a host, comprising:
Obtaining first behavior or status information associated with the host;
Obtaining second behavior or status information associated with a plurality of other hosts having characteristics in common with the host;
Generating one or more behavior or situation criteria for the goal based on the acquired first information and the acquired second information;
Generating the goal based on the generated criteria;
Said method.   Further comprising providing a predetermined goal that includes at least one behavior or status criterion, wherein generating the goal is the at least one of the predetermined goals based on the generated one or more behavior or status criteria. 53. The method of claim 52, comprising modifying one behavior or situation criteria. Providing the generated target for presentation via a human detectable interface;
Receiving a message to activate the goal;
54. The method of claim 52 or 53, further comprising: Obtaining the behavior or situation information is
Capturing a value from a pre-specified input indicative of a behavior or situation associated with the physiological state of the host;
Periodically storing additional values received from the pre-specified inputs, creating a record of user-specific pre-specified input values;
Periodically determining behavior or status information about the host based on a record of user-specific pre-specified input values captured over time;
55. The method of any of claims 52-54, comprising:   56. The method of any of claims 52-55, further comprising transmitting the determined behavior or status information regarding the host.   57. The method of claim 56, wherein transmitting comprises transmitting to at least one of a continuous monitoring device, a patient record system, a smartphone, or a social media internet site.   The pre-specified input includes at least one of a blood glucose meter, a thermometer, an accelerometer, a camera, a microphone, a query processing engine, an electronic device configured for communication between machines, or an electronic patient record. 58. The method according to any one of claims 54 to 57.   59. The method of any of claims 54-58, wherein storing additional values periodically includes storing a time stamp indicating when a particular additional value was stored.   60. The method of any of claims 54-59, wherein the physiological condition comprises one or more of diabetes, obesity, malnutrition, hyperactivity, depression, fertility. Determining behavior or status information about the host includes
Selecting one of a plurality of pre-specified input values included in the record;
Identifying one or more behaviors or situations based on a comparison of the selected input value and the input that provides the selected value with an identification value associated with a plurality of behaviors or situations;
61. The method of any of claims 54-60, comprising:   62. The method of any of claims 54-61, wherein determining behavior or status information about the host comprises processing the pre-identified input values included in the record.   64. The method of claim 62, wherein the processing of the value includes identifying a trend for the value. An integrated system for monitoring glucose concentration in a host and for delivering insulin to the host,
A continuous glucose sensor configured to measure glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
64. A processor module configured to perform any of the methods of claims 52-63;
The integrated system comprising: An electronic device for monitoring glucose concentration in a host,
A continuous glucose sensor configured to measure the glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
64. A processor module configured to perform any of the methods of claims 52-63;
The electronic device comprising: An electronic device for delivering insulin to a host,
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
64. A processor module configured to perform any of the methods of claims 52-63;
The electronic device comprising: A system for adaptive configuration of an analyte monitoring device comprising:
An input receiver configured to receive at least one of status information, behavior information, or physiological information about the host over a period of time;
An input processor configured to identify a situation or behavior based at least in part on information received over time;
An adaptive engine configured to provide adaptive targeting to the analyte monitoring device based on the identified situation or behavior;
Comprising the system. An adaptive teaching method,
Identifying the need for training or requested guidance based on behavior / situation information about the host;
Providing training or guidance in response to the identified need, wherein the training or guidance is based on physiological information associated with the behavior / situation information about the host;
Said method.   69. The method of claim 68, wherein the behavior or context information comprises a structured query or a natural language query.   70. The method of claim 68 or 69, further comprising receiving feedback associated with the training or instruction and reprocessing the training or instruction further considering the received feedback.   71. Any of claims 68-70, wherein the need for training or requested instruction is identified based on a determined goal, the goal being determined based on behavior or status information of the host. The method of claim. Determining the behavior or situation information includes
Capturing a value from a pre-specified input indicative of a behavior or situation associated with the physiological state of the host;
Periodically storing additional values received from the pre-specified inputs, creating a record of host-specific pre-specified input values;
Periodically determining behavior or status information about the host based on a record of the host-specific pre-identified input values captured over time;
72. The method of any of claims 68-71, comprising:   The method of claim 72, further comprising transmitting the determined behavior or status information regarding the host.   The pre-specified input includes at least one of a blood glucose meter, a thermometer, an accelerometer, a camera, a microphone, a query processing engine, an electronic device configured for communication between machines, or an electronic patient record. 74. The method of claim 72 or 73.   75. The method of any of claims 72-74, wherein storing additional values periodically includes storing a time stamp indicating when a particular additional value was stored.   76. The method of any one of claims 72 to 75, wherein the physiological condition comprises one or more of diabetes, obesity, malnutrition, hyperactivity, depression, fertility. Determining behavior or status information about the host includes
Selecting one of a plurality of pre-specified input values included in the record;
Identifying one or more behaviors or situations based on a comparison of the selected input value and the input that provides the selected value with an identification value associated with a plurality of behaviors or situations;
77. The method of any one of claims 72 to 76, comprising:   78. The method of any one of claims 72 to 77, wherein determining behavior or status information about the host comprises processing the pre-identified input values included in the record.   79. The method of claim 78, wherein the processing of the value includes identifying a trend for the value. An integrated system for monitoring glucose concentration in a host and for delivering insulin to the host,
A continuous glucose sensor configured to measure glucose concentration at a host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 68-79;
The integrated system comprising:   A device substantially as shown and / or described in the specification and / or drawings.   A method substantially as shown and / or described in the specification and / or drawings.   A system substantially as shown and / or described in the specification and / or drawings. An electronic device for monitoring glucose concentration in a host,
A continuous glucose sensor configured to measure the glucose concentration at the host substantially continuously and provide continuous sensor data associated with the glucose concentration at the host;
A processor module configured to perform any of the methods of claims 68-79;
The electronic device comprising: An electronic device for delivering insulin to a host,
An insulin delivery device configured to deliver insulin to the host and operably connected to the continuous glucose sensor;
A processor module configured to perform any of the methods of claims 68-79;
The electronic device comprising: A system for adaptive configuration of an analyte monitoring device comprising:
An input receiver configured to receive at least one of status information, behavior information, or physiological information about the host over a period of time;
An input processor configured to identify a situation or behavior based at least in part on information received over time;
An adaptive engine configured to provide adaptive guidance to the analyte monitoring device based on the identified situation or behavior;
Comprising the system.

Images